Agent Transfer Protocol (AGTP)

Agent Transfer Protocol (AGTP) Nomotic, Inc.

chris@nomotic.ai https://nomotic.ai

Applications and Real-Time Independent Submission AI agents agentic systems protocol agent traffic agent transfer This document defines the Agent Transfer Protocol (AGTP): a transfer protocol for AI agent traffic. AGTP carries agent identity, authority, delegation, and attribution as protocol elements of every exchange, on an eighteen-method floor of intent-named methods, over TCP/TLS or QUIC on IANA-assigned port 4480 and the IANA-registered agtp:// URI scheme. The method vocabulary beyond the floor, the path grammar, and the endpoint contract are specified in ; runtime negotiation of endpoints is specified in ; the agent identity document in ; transport bindings in . Version 10 adds per-request proof of possession, so that a verified identity document and a live sender are bound by signature; specifies the Delegation-Chain header with pre-authorization semantics (per-hop scope attenuation checked at mint and at verify, parent re-verification at each hop, depth and cycle limits, and defined failure behavior); maps the delegation model onto the WIMSE chain convention; resolves the 262 and 455 status codes by obtainability; adds structured failure fields to the status code model, states the protocol's position in the transfer-protocol vocabulary throughout, and moves module material to companion specifications so that this document carries the protocol and only the protocol. AGTP is designed to compose with existing agent frameworks, which keep their own semantics and development paths.

Introduction

Conventions and Specification Status AGTP is a transfer protocol. A transfer protocol defines the semantics of an exchange: its methods, status codes, header fields, and, in AGTP, the identity, authority, delegation, and attribution carried with every exchange. A transport protocol delivers the bytes. TCP, TLS, and QUIC are transport; AGTP runs over them as specified in . Throughout this document "transport" refers to those protocols and never to AGTP, and "substrate" names the role AGTP plays beneath agent group messaging protocols. Every mechanism this document names is in one of four states, and the text says which when the state is anything other than specified:

Specified:: The mechanism is defined normatively in this document.
Specified and implemented:: Specified, and present in the reference implementation at github.com/nomoticai/agtp.
Planned:: Named, with its carrier reserved, and specified in a later revision. A planned mechanism guarantees nothing in the current revision.
Inherited:: Provided by a companion specification or an external standard. The dependency is named and the behavior when it is absent is stated.

A header field or body field is a carrier. A carrier by itself implies no claim; the claim exists when the verifier, the verification rule, and the failure behavior are specified. Note Regarding Intellectual Property: Implementers should be aware that extensions and certain mechanisms referenced in this document (the Agent Certificate extension of , the ACTIVATE method, the Agent Genesis mechanism, and the .agent and .nomo file format specifications of ) may be subject to pending patent applications by the author. The core AGTP specification is intended for open implementation without royalty obligation. The licensor is prepared to grant a royalty-free license to implementers consistent with . IPR disclosures: https://datatracker.ietf.org/ipr/; see also the Intellectual Property Considerations subsection of the Security Considerations.

Background The deployment of AI agents and multi-agent systems is accelerating across enterprise, research, and consumer contexts. These systems execute complex, multi-step workflows, querying data sources, booking resources, delegating subtasks to peer agents, and escalating decisions to human principals, with minimal or no human supervision per transaction. Unlike human-initiated web traffic, agent-generated traffic is dynamic, high-frequency, intent-driven, and often stateful across sequences of related requests. The infrastructure carrying this traffic was never designed with these properties in mind.

Limitations of HTTP for Agent Traffic HTTP has served as the internet's primary application-layer transport for over three decades. Its evolution through HTTP/2 and HTTP/3 has improved performance, multiplexing, and latency. However, the fundamental model of HTTP being stateless, resource-oriented, human-initiated request/response, creates specific failures when applied to agentic systems at scale:

Traffic indistinguishability: Agent-generated requests are identical to human-initiated requests on the wire. Operators cannot identify, route, or govern agent traffic without application-layer instrumentation.
Method vocabulary mismatch: HTTP's method set (GET, POST, PUT, DELETE, PATCH) describes resource operations. Agent traffic expresses purposeful intent, summarize, book, delegate, escalate. The mismatch forces intent into request bodies, invisible to protocol-level handlers.
Identity and attribution absence: HTTP carries no native mechanism for asserting agent identity, declared authority scope, or the principal accountable for an agent's actions.
Session semantics mismatch: HTTP's stateless model is optimized for isolated request/response cycles. Agent workflows are stateful sequences.

Why Not Evolve HTTP? A natural question is whether these limitations could be addressed by extending HTTP instead of defining a new protocol. There are three specific reasons why HTTP extension is the weaker path. First, the wire image. HTTP's method registry is extensible under , and new methods can be registered; the constraint is the deployed base. An intent-named method such as SUMMARIZE, DELEGATE, or ESCALATE registered for HTTP would reach every HTTP client, proxy, cache, and middleware component as an unknown method, each handling it by its own default. AGTP instead presents a distinct wire image, with its own URI scheme and port, so that an intermediary either understands agent traffic or sees that it fails to, and nothing in the HTTP deployed base is asked to change its behavior. The case rests on this distinctness and on the failure cases documented in ; HTTP's registry imposes no limit that the case depends on. Second, HTTP carries decades of backward-compatibility constraints. Features such as persistent agent identity headers, authority scope declarations, and session-level governance semantics would require HTTP extensions that interact unpredictably with existing caching, proxy, and CDN behavior designed for human-generated traffic patterns. Third, the observability goal making agent traffic distinguishable from human traffic at the infrastructure layer cannot be achieved by adding fields to HTTP. Infrastructure components route and filter HTTP traffic based on methods and headers that are identical across agent and human requests. A protocol-level separation is necessary to give infrastructure the signal it needs. AGTP is therefore designed as a dedicated protocol. HTTP and AGTP coexist: human traffic continues to flow over HTTP; agent traffic flows over AGTP. The two protocols serve different classes of network participant. Note: The abbreviation AGTP is used in this document to distinguish the Agent Transfer Protocol from the Authenticated Transfer Protocol (ATP) working group currently chartered within the IETF. The URI agtp:// is proposed for IANA registration as a new and distinct scheme.

Motivation for a Dedicated Protocol These limitations are architectural. They cannot be resolved by better middleware or application code layered on HTTP. They require a protocol designed from first principles for AI agent systems. AGTP is that protocol. It provides a dedicated transport environment for agent traffic with: native intent-based methods, mandatory agent identity headers, protocol-level authority scope declaration, and a status code vocabulary for the conditions AI systems encounter.

Scope and Target Audience This document covers AGTP architecture, design principles, stack position, request and response header format, agent-native method definitions and semantics, status code vocabulary, security considerations, and IANA considerations. The Agent Certificate extension for cryptographic binding of agent identity to AGTP header fields is described at a high level in . Full specification is provided in a separate companion document: . That extension may be subject to pending intellectual property claims; see and the IPR Notice preceding the Abstract. Merchant-side identity verification for PURCHASE counterparties is described at a high level in the Merchant Identity section of this document and specified in full in a separate companion: . This document registers the merchant-related request headers, the 458 Counterparty Unverified status code, and the merchant and intent Authority-Scope domains; the Merchant Manifest Document, Merchant Agent Genesis, counterparty verification procedure, and Intent Assertion JWT format are specified in the companion. Target audience: AI agent developers, protocol designers, cloud and network infrastructure providers, enterprise security and compliance architects, and standards community participants.

AGTP as the Transport Foundation for Agent Group Messaging Protocols AGTP is the purpose-built transport and governance layer for Agent Group Messaging Protocols (AGMPs): the category of higher-layer AI agent messaging standards that includes the Model Context Protocol (MCP) , the Agent-to-Agent Protocol (A2A) , the Agent Communication Protocol (ACP) , and emerging others. AGMPs define what agents say. AGTP defines how those messages move, who sent them, and under what authority. AGTP provides the narrow-waist foundation that AGMPs inherit without modification: intent-native methods, mandatory agent identity and scoping, resource budget enforcement, observability hooks, and normative composition profiles. A deployment running any AGMP over AGTP gains transport-level governance without changes to the messaging layer. The AGMP category term is introduced in this document to provide a stable collective reference for the class of protocols that AGTP serves as substrate. It is a descriptive label and classification, with no standing as an IETF term of art. Individual AGMP specifications retain their own names and development paths; AGTP governs none of them, modifies none of them, and leaves each in force.

AGTP as Substrate for AGMPs

Terminology The key words "MUST", "MUST NOT", "REQUIRED", "SHALL", "SHALL NOT", "SHOULD", "SHOULD NOT", "RECOMMENDED", "NOT RECOMMENDED", "MAY", and "OPTIONAL" in this document are to be interpreted as described in BCP 14 when, and only when, they appear in all capitals.

Agent:: For the purposes of this protocol, a participant that holds a Canonical Agent-ID issued through Agent Genesis, acts under a principal and an authority scope, proves possession of its signing key per request, and whose actions are attributable. Whether the participant is implemented with a language model is outside the protocol's knowledge; the protocol constrains what the participant can do and makes what it did attributable. The definition is constitutive, in the way a domain name is whatever the DNS delegation chain resolves: a participant is an agent because it was minted inside the system and the system vouches for the minting, and a participant that meets none of these conditions is outside the protocol however it is implemented.
Principal:: The human, organization, or system that authorized an agent to act and is accountable for its actions.
Agent-ID:: A unique identifier for a specific agent instance. Carried in the Agent-ID request header on non-anonymous AGTP requests, and in the agent_id field of the Agent Identity Document.
Owner-ID:: The identifier of the principal (human, organization, or service) on whose behalf an agent operates. Carried in the agent identity document referenced by Agent-ID; also surfaced as the Owner-ID request header when explicit wire-layer carriage is needed. The locked identifier name throughout the AGTP family is Owner-ID; earlier drafts used Principal-ID, now retired. See .
Authority-Scope:: A declared set of permissions defining what actions an agent is authorized to take, in the format domain:action or domain:*. Declared in the agent's identity document. MAY be carried on individual requests as a claimed-scopes header narrowing the agent's full authorized set to those needed for the request; claimed scopes MUST be a subset of the document's declared set.
Intent Method:: An AGTP method name expressing the agent's purpose, as distinguished from HTTP resource-operation verbs.
Delegation Sequence:: The ordered set of DELEGATE invocations, each a signed hop from a delegating agent to a sub-agent, that produced the current request. Reconstructable from the hop records and verified per .
Delegation-Chain:: The request header that carries the Delegation Sequence as an ordered list of canonical Agent-IDs, origination to current, and the per-hop delegation tokens. Specified in .
Escalation:: An agent's intentional deferral of a decision or action to a human principal or higher-authority agent.
Attribution Record:: A logged record of an agent action sufficient for audit and compliance purposes.
Session:: An AGTP persistent connection context shared across multiple method invocations within a single agent workflow.
SEP (Scope-Enforcement Point):: An AGTP-aware infrastructure component, load balancer, gateway, and proxy, that enforces Authority-Scope compliance without application-layer access. Requires the Agent Certificate extension ().
Agent Package (.agent):: A portable, open deployment artifact for an AI agent. An .agent file contains an embedded Agent Manifest, an integrity hash covering all package contents, and a behavioral trust score computed at packaging time. The .agent format is an open specification. It is analogous to a container image: a self-describing, portable unit of deployment. The .agent suffix is a file format designator and MUST NOT appear as a hostname component or top-level label in agtp:// URIs. Note: the .agent file format specification may be subject to pending patent claims by the author; see .
Governed Agent Package (.nomo):: A deployment artifact in the .nomo format, which extends the .agent format with a CA-signed certificate chain binding the package to a verified governance zone and issuing principal. The .nomo format is to .agent as HTTPS is to HTTP: the same structural foundation with an added layer of cryptographic trust. A .nomo package is required for agents operating at Trust Tier 1 (see ). The .nomo suffix is a file format designator and MUST NOT appear as a hostname component in agtp:// URIs. The name derives from the Greek nomos (νόμος), meaning law, rule, or governance, the same root that underlies autonomy (self-law), nomocracy (rule of law), and onomastics. A .nomo package is literally an agent operating under law: its behavior is bounded by a cryptographically enforced governance context at the packaging layer. Note: the .nomo file format specification may be subject to pending patent claims by the author; see .
Agent Transfer Document (.agtp):: The wire-level manifest document format defined by this specification. An .agtp document is a signed JSON structure containing the fields defined in (Agent Identity Document). It is the output format returned by all AGTP URI resolution requests. Both .agent and .nomo packages produce .agtp documents when queried; the .agtp format is the protocol's canonical representation of agent identity and is independent of the underlying packaging format. The .agtp suffix MAY appear in filenames for stored manifest documents but MUST NOT appear in agtp:// URIs. The Content-Type for .agtp documents is application/vnd.agtp+json.
URI (AGTP):: An agtp:// scheme URI that identifies an agent or agent namespace. AGTP URIs are addresses. File extensions (.agent, .nomo, .agtp) MUST NOT appear in canonical AGTP URIs. See for the canonical URI forms and resolution semantics.
Agent Namespace Document:: The signed application/vnd.agtp.identity+json document returned in response to a request targeting an organization's agent registry root (for example agtp://acme.tld/agents). Lists every Active agent registered under the organization's governance zone. Generated and re-signed by the governance platform on any registry change, with no manual editing. Specified in ; see .
Agent Identity Document:: The signed application/vnd.agtp.identity+json document a canonical Agent-ID resolves to, returned in response to a request targeting a specific agent (for example agtp://acme.tld/agents/customer-service). Carries the Agent Genesis fields, lifecycle state, behavioral trust score, authority scope set, supported methods, and governance zone. Derived from the agent's .agent or .nomo package, whose integrity hash is verified before the document is served, and verified by the recipient before any field is trusted. Mutable: re-signed on every change. Specified in ; see .
Agent Genesis:: A cryptographically signed origin document issued to an agent at registration time by a governance platform. The Agent Genesis is the genesis record of an agent's existence: it establishes the agent's identity, ownership, authorized scope, behavioral archetype, and governance zone before the agent takes any action. Authority is issued through the Agent Genesis; it is never self-assumed. The Agent Genesis is the source document from which the Agent Identity Document () is derived when an AGTP URI is resolved. The canonical Agent-ID is computed as the 256-bit SHA-256 hash of the Agent Genesis in its canonical-form serialization with the signature field excluded; the canonical form is specified in . In this sense the Agent Genesis functions as the agent's permanent origin record: issued once at creation, permanently bound to the agent, and the authoritative identity record from which all other identity representations derive. Agent Genesis fields map to AGTP protocol elements: agent_id maps to the Agent-ID header on every request; owner is the principal identifier recorded in the agent identity document referenced by Agent-ID (there is no separate header); scope is the Authority-Scope set declared in the agent identity document, optionally narrowed per-request via the Authority-Scope header. See . Anonymous agents are ungovernable. Without an Agent Genesis, there is no mechanism to trace decisions to a responsible principal, enforce scope boundaries, or maintain a meaningful audit trail. The taxonomy is: Agent Genesis (the permanent signed governance- layer origin document) → canonical Agent-ID (the 256-bit hash of the Agent Genesis, used in all AGTP protocol operations) → Agent Certificate (an optional X.509 v3 credential for TLS mutual authentication; specified in ). Note: the Agent Genesis mechanism may be subject to pending patent claims by the author; see .
Governance Token:: A signed, time-limited JWT artifact issued by a governance runtime that encodes a specific governance decision for a specific action. Governance tokens are the runtime companion to the static Agent Genesis: where the Agent Genesis establishes persistent identity, the Governance Token carries a bounded authorization for a single action or session. Tokens carry the governance verdict (ALLOW, DENY), the agent ID, action details, trust score dimensions, issuer identity, and expiry. Default TTL: 30 seconds. Tokens MUST NOT be reused across actions; each action requires a fresh evaluation and a fresh token.
Trust Tier:: A classification assigned to an agent based on the strength of identity verification backing its registration. Tier 1 (Verified): org anchor is a real DNS domain with confirmed ownership and a .nomo governed package. Tier 2 (Org-Asserted): org label is present but DNS ownership is unverified; .agent package acceptable. Tier 3 (Experimental): X- prefix required; undiscoverable through the public AGTP registry. See .
AGMP (Agent Group Messaging Protocol):: The collective term for higher-layer AI agent messaging standards that operate over AGTP as their transport substrate, including MCP , A2A , ACP , and ANP . AGMPs define what agents say to each other. AGTP defines how those messages move. The term is introduced in this document as a descriptive classification and has no standing as an IETF term of art.
DESCRIBE:: An AGTP cognitive floor method that returns the declared capabilities, supported modalities, method vocabulary, and versioned feature set of a specific agent endpoint. Distinguished from URI resolution (which returns identity) by returning operational capability metadata suitable for pre-task negotiation. If the capability_domains parameter is omitted, the server SHOULD return all supported domains. Category: ACQUIRE.
SUSPEND (method):: An AGTP mechanics floor method that places a specific active session workflow into a recoverable paused state, issuing a resumption nonce for re-entry. Distinguished from the lifecycle SUSPEND event (): method-level SUSPEND is session-scoped and leaves the agent's registry lifecycle state and Agent Genesis unchanged validity. Category: ORCHESTRATE.
Budget-Limit:: A request header declaring the maximum resource consumption the principal authorizes for a method invocation, expressed as comma-separated unit=value tokens drawn from the IANA AGTP Budget Unit Registry per list-valued header conventions. Example: Budget-Limit: tokens=5000, compute-seconds=120, financial=10.00USD, ttl=3600. Exceeding the declared limit MUST cause the server to stop execution and return 456 Budget Exceeded. Note: ttl= is RECOMMENDED to bound budget lifetime. Specified in ; see .
AGTP-Zone-ID:: A request header declaring the network zone or organizational boundary within which a request must be processed. Scope-Enforcement Points (SEPs) MUST enforce zone boundaries and MUST return 457 Zone Violation if a DELEGATE request would route outside the declared zone.
Identity-first architecture:: The architectural commitment that the canonical Agent-ID (256-bit content-addressed identifier) is the authoritative identity primitive in AGTP. Hosting, DNS anchors, and other resolution paths are aliases.
Intent Verb:: An AGTP method name expressing the agent's purpose, as distinguished from HTTP resource-operation verbs (GET, POST, PUT, DELETE). The vocabulary is specified in .
Scope-Enforcement Point (SEP):: An AGTP-aware infrastructure component (load balancer, gateway, proxy) that enforces Authority-Scope compliance on AGTP requests without application-layer access. Line-rate enforcement requires .

Document Taxonomy AGTP identity rests on three objects with one join key. The canonical Agent-ID is the SHA-256 of the Agent Genesis, so the Genesis is the root; the Agent-ID resolves to the Agent Identity Document; the Attribution-Record chain records what the agent did, anchored back to the Genesis through the Audit-ID of . AGTP Identity Objects

Object	Answers	Signed by	Changes	Specified in
Agent Genesis	who this agent is, permanently	issuing registrar	never; a change is a new agent	this document
Agent Identity Document	what this agent is now	the agent's issuer	re-signed on each change
Agent Namespace Document	which agents a namespace hosts	namespace operator	re-signed on each registry change
Attribution-Record and Audit-ID chain	what this agent did	the acting agent, per action	append-only	this document,

Two terms outside this taxonomy appear in related work. "Agent Birth Certificate" is the retired name for the Agent Genesis; the object is unchanged. "Agent Card" names the A2A self-description served at a well-known HTTPS path and trusted through its domain; it is self-asserted, unsigned, and carries no lifecycle state or enforced scope. An Agent Identity Document maps to an Agent Card for interchange with a loss of those properties ( specifies the mapping); an Agent Card maps to an Identity Document only at Level 1, with no issuer. An Agent Card and an Identity Document are different objects, and this family uses neither name for the other.

Architectural Principles AGTP's design follows five architectural principles that distinguish it from incremental extensions to HTTP and from policy-layer approaches to agent governance. These principles motivate the specific protocol decisions in the rest of this document; they also explain why certain vulnerability classes that affect HTTP-based agent infrastructure are impossible to express on AGTP, which is a stronger claim than mitigation. The principles are stated abstractly so they apply beyond any specific example (such as the BadHost vulnerability discussed in ). A reviewer evaluating whether AGTP succeeds at its design goals should ask whether the protocol satisfies all five principles; any single concrete vulnerability is a weaker test.

Substrate vs Application Layer Separation AGTP provides substrate primitives. Adjacent layers (Agent Group Messaging Protocols, external identity providers, HTTP gateways, agent application logic) compose over the substrate. The substrate MUST NOT rely on application-layer cooperation for properties it provides; it MUST enforce them itself at the transport boundary. This principle has direct consequences:

Identity headers (Agent-ID, Owner-ID, Authority-Scope) are wire- layer facts the substrate verifies before dispatch to the application. They are never application-layer conventions an application is expected to honor.
Authority enforcement happens at the protocol layer before application code runs. A scope violation returns 455 from the AGTP layer, before the application's authorization middleware is reached.
Attribution is produced by the substrate on every response. An application cannot opt out of attribution, fail to produce it, or produce a malformed attribution that infrastructure cannot read.

The substrate's correctness is independent of the application implementing required behaviors. Vulnerabilities of the form "middleware was supposed to check X but checked Y instead" cannot arise in the substrate layer because the substrate enforces X itself, before any middleware runs.

Identity at the Wire Agent identity is a wire-layer fact in AGTP. On HTTP it is an application-layer convention reconstructed from request properties. Every AGTP request carries Agent-ID and Authority-Scope as structured headers verified at the AGTP layer, with Owner-ID resolved from the identity document the Agent-ID references (). Infrastructure components (load balancers, Scope-Enforcement Points, governance gateways) read these directly from the wire. They never reconstruct identity from hostnames, paths, query parameters, or application payloads. They never parse application content to determine which agent sent a request. This principle eliminates an entire vulnerability class: bugs where application-layer code reconstructs identity (or authority, or routing decisions) from request properties that an attacker can manipulate. The reconstruction surface is absent in AGTP because identity is read from headers the protocol parses as identity; no header parsed for another purpose is ever reinterpreted as identity. Vulnerabilities affecting HTTP-based agent infrastructure that depend on host header manipulation, URL reconstruction, path-based authorization middleware, or similar reconstruction patterns are structurally impossible on AGTP because AGTP never reconstructs identity from those properties. Agent identity and workload identity are different concerns that compose. A workload identity credential of the kind the IETF WIMSE working group specifies authenticates the workload an agent runs on; the AGTP agent identity, bound to a certificate through , persists across the workloads that host it. A mature deployment carries both, and neither substitutes for the other. AGTP addresses both roles the agent literature distinguishes: the user agent, which acts for a person and owes that person loyalty, and the service agent, which acts for an organization and offers a capability to others. Every mechanism in this document holds for both. What differs is the Owner-ID the Identity Document carries, a person or an organization, and the governance policy that owner sets. The loyalty, protection, and honesty obligations of a user agent are that policy's content; the protocol carries the accountable owner and leaves the obligations to the owner and the governance platform.

Heteronomy: Agents Are Created by Humans Agents lack autonomy in the strong sense. Every agent has a creator, an owner, and a governance context established outside the agent's own operation. AGTP's identity primitives reflect this fact.

The Agent Genesis is signed by a registrar before any agent traffic exists. The Agent Genesis is the permanent governance-layer record of the agent's existence; the agent never creates its own Genesis.
The Owner-ID identifies the human or organizational principal accountable for the agent. The owner is recorded on the Agent Genesis at registration; the agent asserts nothing about its owner at runtime.
The Authority-Scope is granted by a principal at registration; the agent claims nothing at runtime that the grant omits. An agent MAY narrow its claimed scope on a specific request below its declared scope; an agent MUST NOT claim scope beyond what its Genesis grants.
The Agent Certificate is issued by a Certificate Authority that validates the agent's Genesis-anchored identity. The certificate confirms an identity established outside the certificate; it asserts no identity of its own.

This architectural principle distinguishes AGTP from approaches that treat agents as self-asserting entities. An agent cannot register itself; an agent cannot grant itself authority; an agent cannot issue its own certificate. The trust root is the human or organizational authority that created the agent. AGTP makes this trust root visible at the wire layer through the identifier chain (Agent-ID, Owner-ID, issuing registrar). The implications for governance, attribution, and accountability are substantial. An agent operating outside its granted authority is a governance failure (the protocol structurally prevents the out-of-scope action, so the protocol itself has held) traceable to the principal who granted the authority, the registrar who recorded it, or the operator who deployed the agent, each of whom the wire identifies.

Structural Enforcement, Not Policy Enforcement Security properties in AGTP are structural --- they hold because the protocol's design eliminates the architectural pattern that creates the vulnerability, with no dependence on operators enforcing a policy correctly or middleware checking the right field. The distinction matters in two ways: Vulnerability impossibility vs vulnerability mitigation. A structural property holds because the protocol cannot express the vulnerable configuration. A policy property holds because operators correctly configure and enforce it; misconfiguration restores the vulnerability. AGTP's design prefers structural properties wherever the architecture allows. Defense in depth vs defense by configuration. AGTP composes with application-layer security (input validation, application-specific authorization, business logic enforcement). AGTP leaves in place these. AGTP provides primitives that compose with application-layer security so that the combined system is stronger than either layer alone. Concrete example: the BadHost vulnerability class (CVE-2026-48710 and similar) exists because HTTP-based agent infrastructure reconstructs URLs from the Host header and operates path-based authorization on the reconstruction. AGTP eliminates this vulnerability class by having no Host header to check, by parsing path and query as separate wire-layer tokens with no URL reconstruction, and by enforcing authorization on Authority-Scope with the path playing no part. The vulnerable configuration cannot be expressed on AGTP because AGTP lacks the architectural pattern that produces the vulnerability. This principle applies to other vulnerability classes as well: scope escalation through header manipulation, attribution forgery through log gaps, and identity spoofing through certificate confusion are addressed by the structure of the protocol, with no policy to enforce.

Substrate Carries Its Own Operational Properties Identity, authority, attribution, delegation chain, trust posture, and session state are properties of the substrate itself. Applications inherit them and layer nothing on to supply them. This principle enables uniform infrastructure handling regardless of which adjacent layer is composed. An infrastructure component (load balancer, Scope-Enforcement Point, governance gateway, monitoring system) processes AGTP traffic identically whether the payload is an MCP tool call, an A2A task, an OAuth-credentialed request, an HTTP gateway translation, or a future protocol yet to be designed. The substrate's operational properties are visible to infrastructure at the wire layer. The principle has economic and operational consequences:

One governance layer covers all agent traffic. Operators never need separate enforcement for each AGMP. The AGTP governance layer handles MCP, A2A, ACP, ANP, and any future protocols uniformly.
Audit and attribution compose across protocols. An attribution record produced by an EXECUTE invocation carrying an MCP tool call has the same structure as an attribution record produced by an EXECUTE invocation carrying an A2A task. Audit consumers never need protocol-specific parsing.
Future-proof composition. Adjacent layers yet to be defined can compose with AGTP using the existing substrate properties. New AGMPs, new identity providers, new translation patterns benefit from substrate properties without negotiating each property anew.

Adjacent layers benefit from substrate properties without needing to implement them. Composition works because the substrate carries identity, authority, attribution, and audit; adjacent layers focus on what they contribute (tool semantics, conversational structure, authorization framework, REST translation).

Problem Statement AGTP is motivated by three distinct, compounding failures in how current internet infrastructure handles AI agent traffic.

Problem 1: Undifferentiated Agent Traffic on HTTP AI agents generate intent-driven, structured traffic that is functionally invisible to the infrastructure it traverses. This traffic flows through HTTP alongside human traffic with no protocol-level differentiation. Observability failure, routing inefficiency, and security blindness result, operators cannot determine what fraction of traffic is agent-generated without application-layer instrumentation that is expensive, inconsistent, and easy to circumvent. AGTP response: a dedicated protocol environment for agent traffic. Infrastructure can distinguish, route, monitor, and govern agent traffic natively.

Problem 2: Semantic Mismatch Between Agent Intent and Available Methods AI agents operate on intent. HTTP's method vocabulary was designed to describe operations on resources; purposeful action has no place in it. When an agent intends to SUMMARIZE a document, EXECUTE a reservation, and PLAN a sequence, all three arrive as POST requests. The server receives identical verbs with meaningfully different intent buried in request bodies, invisible to any protocol-level handler. AGTP response: a vocabulary of agent-native methods that express intent at the protocol level.

Problem 3: No Protocol-Level Identity, Authority, or Attribution for Agents When an AI agent takes an action, there is currently no protocol-level mechanism to verify who authorized this agent, what scope of authority it holds, which principal is accountable for its actions, or whether it is the agent it claims to be. Accountability gaps, authority laundering, auditability failure, and multi-agent trust collapse result. AGTP response: agent identity and authority scope embedded in protocol headers on every request, with an optional Agent Certificate extension for cryptographic verification.

Problem Summary Summary of Problems Addressed by AGTP

#	Problem	Current Failure	AGTP Response
1	Undifferentiated traffic	HTTP cannot separate agent traffic	Dedicated protocol environment
2	Semantic mismatch	HTTP verbs obscure agent intent	Native intent-based method vocabulary
3	No protocol-level identity	Attribution is untraceable	Agent identity and scope in headers

Related Work and Existing Approaches

HTTP/REST as the De Facto Standard HTTP remains the universal transport for all agent traffic currently deployed. REST conventions layered on HTTP provide a degree of semantic structure, but REST remains a resource-manipulation paradigm. As described in , evolving HTTP to address agent-specific needs is constrained by the frozen method registry, backward-compatibility requirements, and the impossibility of achieving infrastructure-level traffic differentiation through HTTP extensions alone.

Existing Agent Group Messaging Protocols

MCP (Model Context Protocol, Anthropic):: Defines structured communication between AI models and tools/resources. Runs over HTTP. Addresses tool-calling semantics; the carriage of agent traffic is outside it.
ACP (Agent Communication Protocol, IBM):: Defines messaging semantics for agent-to-agent communication. Runs over HTTP.
A2A (Agent-to-Agent Protocol, Linux Foundation):: Defines inter-agent communication and task delegation semantics. Runs over HTTP.
ANP (Agent Network Protocol):: Defines discovery and communication for networked agents. Runs over HTTP.

All of these are messaging protocols. They define what agents say to each other. None of them defines how agent traffic moves across a network. Each presupposes HTTP as its transport and inherits all of HTTP's limitations for agentic systems.

Transfer and Transport Alternatives

gRPC:: High-performance RPC over HTTP/2. Strong typing and efficient serialization. Leaves agent-specific semantics, identity, and authority.
WebSockets:: Persistent bidirectional connections over HTTP. Useful for real-time communication but leaves method semantics and identity unaddressed.
QUIC :: Modern multiplexed transport with reduced connection overhead. QUIC is a transport primitive; AGTP is the application-layer protocol above it. AGTP's QUIC transport binding is specified in .

The Critical Distinction: Messaging vs. Transfer The most important positioning principle for AGTP is the distinction between message formats and the transfer protocol that carries them. MCP, ACP, A2A, and ANP are messaging protocols: they define what agents say to each other. AGTP is the transfer protocol: it defines the exchange that moves those messages, and the identity, authority, and attribution carried with each one. An analogy: HTTP transfers HTML. HTML defines what a page says; HTTP defines the exchange that delivers it, with its own methods, status codes, and headers. HTML cannot replace HTTP, and saying "HTTP is unnecessary because HTML exists" is a category error. SMTP and the Internet Message Format stand in the same relation. MCP and its peers are the message formats of agent traffic. AGTP is the transfer protocol, and TCP, TLS, and QUIC beneath it are the transport.

Discovery and Naming Agent discovery is specified in and , and this document carries only the identity commitments those documents build on. The Canonical Agent-ID is permanent identity; the current location of an agent is a short-lived, signed, updatable record the substrate resolves it to. Following RFC 6763, "discover" names the resolution of a known identity to a reachable attachment, and "search" names the capability-class query that returns candidate identities. An agent name (a friendly label or a domain-anchored alias) and an agent address (a URL or network address) are aliases for the Agent-ID; the identity is the Agent-ID alone. Work on agent discovery in the IETF DAWN effort is treated as adjacent in , which specifies the mapping between the AGTP Agent Identity Document () and the record shape the DAWN work describes agents with (the A2A AgentCard in its initial revision).

AGTP Positioning: The Proposed Stack

AGTP in the Protocol Stack AGTP replaces no messaging protocol. Agents using MCP or A2A route those messages over AGTP and gain transport-level observability and identity without modifying the messaging layer. AGTP-native agents that use no separate messaging protocol interact with AGTP methods directly.

Protocol Overview

Stack Position AGTP is an application-layer protocol. It operates above the transport layer and is wrapped by TLS. It sits below any agent messaging protocol in deployments that use one. AGTP is transport-neutral: AGTP semantics are independent of which transport carries them. Transport bindings for TCP/TLS and QUIC are specified in , including the AGTP-specific replay- safety profile that governs early-data use over QUIC. Selection between supported transports is a deployment-time choice based on operator infrastructure, counterparty ecosystem, and latency requirements; this specification establishes no normative preference between transports. AGTP uses port 4480 (TCP and UDP), assigned by IANA under the service names agtp (TCP/TLS) and agtp-quic (QUIC). The port assignment is permanent and applies to all AGTP transports. Full IANA registration metadata is documented in .

Design Principles

Minimalist core:: The base spec defines only what is necessary for agent traffic differentiation, method semantics, and identity headers. Extensions belong in companion specifications.
Extensible by design:: New methods are registered through an IANA-managed Method Registry. New header fields follow a defined extension convention. Additive changes require no version increment.
Agent-native:: Every design decision assumes the initiating party is an AI system. Human-initiated traffic belongs on HTTP.
Secure by default:: TLS 1.3 or higher is mandatory. Unencrypted AGTP connections MUST be rejected. Agent identity headers are present on every request.
Observable by design:: Native metadata in every AGTP header provides the minimum information needed for routing, monitoring, and audit without application-layer instrumentation.
Composable:: AGTP works alongside existing agent messaging protocols without requiring modification to those protocols.
Runtime contract negotiation:: AGTP fixes the protocol surface at eighteen methods. Beyond that floor, the surface is open. An agent that needs an endpoint the server has yet to advertise proposes the endpoint via PROPOSE with an AGTP-METHODS endpoint definition; the server evaluates whether it can synthesize the endpoint from existing capabilities and either instantiates it as a session-scoped endpoint or refuses. The negotiation completes in a single round-trip. See .

AGTP as a Runtime Contract Negotiation Substrate AGTP is a runtime contract negotiation substrate (RCNS). The substrate fixes a floor of eighteen protocol-level methods (the cognitive, mechanics, and lifecycle verbs of ); beyond that floor, the method and endpoint surface a server presents is declared by the operator in the vocabulary of or negotiated at runtime between the agent and the server through the PROPOSE floor method, in a single round-trip, as specified in . This document carries the kernel: the PROPOSE method (), the negotiation status codes 261, 262, 263, 461, 463, and 464 (), the reason vocabulary for 461 and 464, the Allow-RCNS, Contract-Synthesized, and Idempotency-Key headers (), and the rcns_* lifecycle events (). The dispatcher gate, delivery modes, contract scoping and lifecycle, recipe versioning, and the inventory surfaces are specified in . A server that implements this document and without is conformant and refuses unregistered method and path pairs with 404 or 405. The RCNS property makes composition with higher-level agent frameworks () tractable: a server that wants to expose a framework-specific operation as a first-class AGTP endpoint negotiates it at runtime, with no registry to wait for.

Connection Model AGTP uses a persistent session model by default, reflecting the reality that agents typically execute multi-step workflows; an isolated single request is the exception. An AGTP session is established with a single TLS handshake including agent identity assertion, persists across multiple method exchanges, carries a Session-ID header identifying the agent's task context, and terminates on explicit session close or inactivity timeout (RECOMMENDED minimum: 60 seconds). Per-request (stateless) mode is supported for constrained environments. In stateless mode, agent identity headers MUST be present on every individual request.

Wire-Format Framing AGTP requests and responses MUST be framed by an explicit Content-Length header. Content-Length is the sole signal of request and response completion. Receivers MUST treat the message as complete when, and only when, the declared number of body octets has been read after the header terminator. Implementations MUST NOT rely on transport-level connection termination as a request-completion signal in addition to Content-Length. Transport-specific framing requirements, including the prohibition on TLS socket-level half-close and the handling of QUIC stream termination, are specified in . Implementations that require an explicit completion signal in addition to Content-Length MUST rely on the AGTP session-close semantics described in . AGTP uses no chunked transfer encoding. Streaming method responses are framed by repeated Content-Length-delimited messages within a single AGTP session. Real-time media streams between agents (voice, video, sensor data) are specified in , which builds on the session establishment of .

Header Format The AGTP wire format puts the protocol version and method on the request line (AGTP/1.0 METHOD PATH\r\n) and the status code on the response line (AGTP/1.0 STATUS STATUS-TEXT\r\n). Headers MUST NOT carry information already present on those lines: there is no AGTP-Version header, no AGTP-Method header, no AGTP-Status header. The version and method are read from the request line; the status is read from the response line.

Request Line Grammar The request line carries three tokens separated by single space characters, terminated by CRLF: The request-target follows the path-absolute production of , optionally followed by ? and a query string. Path and query are parsed as separate tokens: the path is everything from the leading / up to the first ? or end-of-line; the query string is everything after the first ? up to the CRLF. Servers MUST parse path and query as separate tokens before dispatch, matching URI generic syntax. Implementations MUST NOT treat a ?-prefixed query as part of the path; the path-grammar enforcement in applies to the path component only. URI fragments (#anchor) MUST NOT appear on the request line. A request line containing # MUST be rejected at the wire layer as malformed. The path-pattern grammar (template parameters in {param} form, verb-leakage prevention, structural minimums) is normatively specified in . v07 servers MUST implement the AGTP-METHODS path grammar.

Response Line Grammar The response line carries three tokens separated by single space characters, terminated by CRLF: The status-text is informational and MUST NOT be used by servers or clients for protocol decisions; the numeric status-code is authoritative.

Request Headers AGTP Request Header Fields

Field	Required	Description
Agent-ID	MUST for non-anonymous requests	Canonical 256-bit identifier of the invoking agent. Identifies the request's source; the target is the path. Servers reject requests lacking `Agent-ID` against non-anonymous endpoints.
Authority-Scope	MAY	Scopes the agent claims for this specific request. When present, every claimed scope MUST be a subset of the scopes declared in the agent's identity document; servers MUST validate and MUST return 455 Scope Violation with reason `scope-claim-invalid` on failure, since a claim beyond the document's grant exceeds authority the agent holds. When absent, the request inherits the full scope set of the agent's identity document. The server uses the claimed (or inherited) set when evaluating the endpoint's `required_scopes`.
Session-ID	MAY	Opaque session identifier grouping multiple requests into an operational session. The protocol assigns no semantics; servers pass the value through to handlers via the endpoint context.
Task-ID	MAY	Opaque identifier tracing a specific task or operation across multiple requests. Useful for audit correlation. Servers SHOULD echo this value in the response `Task-ID` header.
Delegation-Chain	MUST on requests made under delegated authority	The Delegation Sequence that produced this request: an ordered list of canonical Agent-IDs, origination to current, with the per-hop delegation tokens. Format, minting, verification, and failure behavior are specified in . Absent on requests the agent makes under its own authority.
Request-Signature	MUST on non-anonymous requests	Proof that the sender holds the agent's current signing key: a compact JWS over the method, path, Agent-ID, Authority-Scope, Delegation-Chain digest, body digest, timestamp, and nonce, per .
Merchant-ID	MUST on PURCHASE	Canonical identifier of the intended merchant counterparty. See .
Merchant-Manifest-Fingerprint	MUST on PURCHASE	SHA-256 fingerprint of the Merchant Manifest Document verified by the requesting agent. Receiving server MUST reject with 458 if this differs from its current manifest. See .
Intent-Assertion	SHOULD on PURCHASE	Detached JWT carrying signed principal-authorized purchase intent. Forwardable to payment networks as standalone evidence. See .
Authorization	MAY	Application-layer authorization credential carried for composition with external identity providers (e.g., OIDC/OAuth bearer tokens, SPIFFE SVIDs). When present, the value follows the HTTP `Authorization` header syntax per (e.g., `Bearer TOKEN`). AGTP identity (Agent-ID, Agent Certificate) and the credential in this header answer different questions and are orthogonal: AGTP identity identifies the requesting agent; the credential in this header identifies the human or service principal on whose behalf the agent acts. Servers MAY require an `Authorization` header on specific methods per `[policies.oauth]` configuration; the External Identity Provider composition profile in defines the normative composition rules. Semantics of any token in the header are application-defined and outside AGTP's wire scope.
Cart-Digest	MAY	Cryptographic digest of a structured cart returned by a prior QUOTE invocation. Binds a PURCHASE to a previously quoted cart without retransmission of line-item detail. See .
Allow-RCNS	MAY	Caller opt-in to Runtime Contract Negotiation. Value `true` signals the caller is willing to receive a 461 RCNS Contract Available response or an inline optimistic synthesis when a requested `(method, path)` pair is unregistered. Absent or non-`true` keeps the RCNS gate closed; the request is then refused per the standard unregistered-pair rules. See .
Contract-Synthesized	MAY	The `synthesis_id` of a previously-issued RCNS contract. Presents the contract to bypass the four-lock gate and dispatch the request directly under the synthesized contract. The server MUST refuse the presentation with `464 contract-not-yours` if the caller's Agent-ID differs from the contract's `originating_agent_id`. See .
Idempotency-Key	MAY	Per-agent idempotency key for RCNS-eligible requests and other state-modifying calls. Servers MUST scope the idempotency cache by `(Agent-ID, Idempotency-Key)`; replays from the same agent return the cached response, replays from different agents are independent. See .

Request Signature and Proof of Possession A verified Agent Identity Document establishes that an Agent-ID exists, who owns it, and what it may do. Whether the sender of a given request is that agent is a separate question the document alone cannot answer. Without a per-request proof, Agent-ID is a self-asserted header bound to a verified document, and any party that can read the document can present the header. The Request-Signature header closes that gap. Every non-anonymous request MUST carry Request-Signature: a compact JWS with algorithm EdDSA, kid equal to the canonical Agent-ID, signed with the private key whose public half is the agent_public_key of the agent's current Identity Document (). The JWS payload is the JSON object: ", "p": "", "aid": "", "as": "", "dc": "", "bd": "", "iat": , "n": "" } ]]> serialized in the canonical form of . The server MUST verify the signature before dispatch and MUST reject the request when: the signature fails under the current agent_public_key; any covered field differs from the request as received; iat is outside the server's acceptance window (default 300 seconds, operator configurable); or the (aid, n) pair has been seen within the window. Rejection is 401 with reason possession-unproven, and the event MUST be logged. Anonymous requests (no Agent-ID) carry no signature and receive only what the server offers anonymously. Key rotation is a re-issuance of the Identity Document with a new agent_public_key by the agent's issuer; the Agent-ID is unchanged, because authority attaches to the agent and the key is replaceable. A verifier caches the document per the freshness rules of and re-resolves on a signature failure before rejecting, so a rotated key is picked up without a round trip in the common case and with one in the worst case. Delegation tokens () are signed with the same key. Identity Documents issued before this revision carry no agent_public_key. A request from such an agent MAY be accepted by operator policy and MUST be recorded as possession-unproven in the Attribution-Record; it is verified at Level 1 () regardless of document verification. Operators SHOULD set a date after which such documents are refused.

Response Headers AGTP Response Header Fields

Field	Required	Description
Server-ID	MUST	Canonical identifier of the server that produced the response. MUST be populated from the server's configured `server_id` on every response. Useful for audit, load-balanced deployments, and verifying which server processed a request. Distinct from `Agent-ID`: `Server-ID` identifies the host that processed the request, `Agent-ID` (when echoed) identifies the requesting agent.
Agent-ID	SHOULD when present in request	Echo of the request's `Agent-ID` header to correlate response with the requesting agent. Absent when the request was anonymous. Echoed verbatim from the request; servers MUST NOT substitute or normalize the value on the response path.
Task-ID	SHOULD when present in request	Echo of the request's `Task-ID` header to correlate response with request. Absent when the request carried no `Task-ID`.
Request-ID	SHOULD when present in request	Echo of the request's `Request-ID` header per the per-interaction identifier convention. See .
Response-ID	MUST	Per-interaction identifier of this response. Distinct from `Request-ID`; together they pair a request and its response on the wire. See .
Audit-ID	MUST when Attribution-Record is present	Identifier of this response's Attribution-Record, computed as `sha256(jws_compact_serialization)` of the Attribution-Record JWS. The same value appears as `previous_audit_id` in the agent's next emitted Attribution-Record, closing the per-agent hash chain. See .
Owner-ID	SHOULD	Identifier of the human or organizational principal accountable for the responding agent. Recorded in the agent's Agent Genesis and stamped on every response by the daemon. See .
Trust-Tier	SHOULD	Resolved trust tier of the responding agent (`1`, `2`, or `3`) per the trust-posture loading rule in . Stamped on every response when the responding server has resolved a trust tier for the addressed agent; omitted when no trust tier is known. Allows relying parties to apply trust-tier-conditional policy on every response without consulting the Agent Identity Document.
Verification-Path	SHOULD when `Trust-Tier` is present	Resolved verification path of the responding agent (`dns-anchored`, `log-anchored`, `hybrid`, or `org-asserted`) per the trust-posture loading rule in . Stamped on every response when the responding server has resolved a verification path; omitted when no path is known.
Trust-Warning	MUST when resolved `Trust-Tier` is `2` and a warning is set	Trust warning token recorded on the responding agent's Agent Identity Document (e.g., `verification-incomplete`, `verification-path-unsupported`). Stamped on every response from a Tier 2 agent so relying parties can surface the warning without consulting the Agent Identity Document; omitted on Tier 1 and Tier 3 responses. See .
Contract-Synthesized	MUST when serving under RCNS optimistic mode	The `synthesis_id` of the contract under which this response was served. Notifies the caller that the response was served under a runtime-negotiated contract per . Callers that wish to repeat the action send subsequent requests with the same header value in the request to bypass the gate.
RCNS-Attempt-Id	MUST on every 464 RCNS No Contract response from an RCNS-capable server	Opaque identifier of the failed synthesis attempt record. Retrievable via `INSPECT target=rcns-attempt` and carries the diagnostic detail for the failure (which gate lock closed, the requested `(method, path)`, the trust tier resolved at evaluation time). See .
Attribution-Record	MUST	JWS-signed attestation of the response's origin, serialized in JWS Compact form per (`base64url(protected_header).base64url(payload).base64url(signature)`). The payload carries the base attribution fields (server ID, response timestamp, request hash, response status) together with the identifier-chain fields and the per-agent chain link (`previous_audit_id`); see for the extended payload schema. Servers with a configured manifest signing key sign the payload with that key; servers without a configured key emit a fallback JWS with `alg: none` and an empty signature octet, preserving the wire format and the Audit-ID chain. Consumers that require cryptographic attestation MUST reject `alg: none` records.
Continuation-Token	MAY	Token for retrieving additional results in streaming contexts.
Supported-Methods	SHOULD (on session open)	List of AGTP methods supported by this server.
Cost-Estimate	MAY	Estimated resource consumption in Budget-Limit unit format. Returned by QUOTE; MAY appear on any response as an informational signal.
Attestation-Evidence	MAY	RATS attestation evidence token or reference URI per . Format indicated by `attestation_type` in response body: `rats-eat`, `rats-corim`, or `rats-uri`.

Implementations MAY emit implementation-specific headers, by convention prefixed X-, but such headers have no protocol semantics; agents MUST NOT rely on them and servers MUST NOT require them.

Headers Planned or Specified Elsewhere The following headers were named in earlier drafts. Two are now specified in companions; the rest are planned, in the status vocabulary of . Servers MUST NOT require a planned header and MAY ignore one when received: Headers Planned or Specified in Companions

Field	Status	Anticipated Use
Priority	Planned	Request priority hint: critical, normal, background
TTL	Planned	Maximum acceptable response latency in milliseconds. Pairs with status code 408 Timeout.
Budget-Limit	Specified in	Maximum resource budget per invocation. Pairs with status code 456 Budget Exceeded.
AGTP-Zone-ID	Planned	Network zone boundary constraint. Pairs with status code 457 Zone Violation; SEP-enforced.
Content-Schema	Specified in	URI reference to the schema describing the request body or carried payload.
Telemetry-Export	Planned	OTLP endpoint URI for metric export, or `inline` to receive metrics embedded in the response `Attribution-Record`.

Status codes 456 Budget Exceeded and 457 Zone Violation remain allocated in the AGTP Status Code Registry; their normative trigger headers (Budget-Limit, AGTP-Zone-ID) are deferred to a future revision. v00 servers MAY enforce equivalent semantics through implementation-specific mechanisms and return the corresponding status code, but the wire-level headers are outside of the v00 contract.

Retired Headers The following headers appeared in earlier drafts and have been removed. Implementations MUST NOT emit them and MAY reject requests that carry them: Retired AGTP Headers

Field	Reason for Removal
AGTP-Version	Redundant with the request and response lines (which carry `AGTP/1.0`).
AGTP-Method	Redundant with the request line (which carries the method token).
AGTP-Status	Redundant with the response line (which carries the status code).
Principal-ID	Renamed to `Owner-ID` in line with the locked AGTP taxonomy. The Owner-ID is recorded in the agent identity document referenced by `Agent-ID` and never transmitted as a separate request header. See .
Server-Agent-ID	Renamed to `Server-ID`. The earlier name conflated server identity with agent identity.

Status Codes AGTP defines its own status code space. Codes 261 through 263, 455 through 465, and 550 through 555 are AGTP-specific with no HTTP equivalent and are registered in the IANA AGTP Status Code Registry (see ). AGTP-specific code numbers are chosen from ranges unassigned in the IANA HTTP Status Code Registry to avoid semantic collision with HTTP status codes that may appear in payloads carried by AGTP method invocations. The AGTP status code model carries four structural rejection codes (404, 405, 459, 460) that together cover the failure surface for contract-level invocation. Each code is independently actionable: 404 indicates the path is absent from this server; 405 indicates the verb and path are each individually valid but the server exposes no endpoint at that combination; 459 indicates the verb is absent from the AGTP-METHODS approved method catalog; 460 indicates the path violates AGTP-METHODS path grammar. The structural rejection model and the curated method catalog are specified in . AGTP Status Codes

Code	Name	Meaning
200	OK	Method executed successfully
202	Accepted	Method accepted; execution is asynchronous
204	No Content	Method executed; no response body
261	Negotiation In Progress	PROPOSE evaluation in progress; agent MAY poll for terminal status. See .
262	Authorization Required	Authorization the agent could obtain is absent: credential establishment, consent, or a scope the endpoint requires that the agent holds in its identity document but omitted from its claim. Never returned when the request exceeds the authority the agent holds; that is 455. Covers PROPOSE-time authorization, unclaimed scope at endpoint dispatch, ad-hoc method invocation requiring wildcards consent, and discovery requests blocked by anonymous-discovery policy. See ; the RCNS gate case is in .
263	Proposal Approved	PROPOSE accepted; the proposed endpoint has been synthesized and instantiated. Response body carries the synthesized endpoint contract. See .
400	Bad Request	Malformed AGTP request
401	Unauthorized	Authentication failure. Covers an unrecognized or unauthenticated Agent-ID, INSPECT read-access ACL failure for unauthenticated callers, lifecycle-method invocation without a verified client certificate when `genesis_issuer` mode is in effect, and external-credential failures (e.g., missing `Authorization` header on a method that requires one, or an `Authorization` header that fails validation). The response body SHOULD carry a structured `reason` from the vocabulary `agent-unauthenticated`, `oauth-required`, `oauth-invalid`, `acl-anonymous-blocked`, or `genesis-issuer-cert-required` to disambiguate the failure mode. See for the External Identity Provider composition profile and the OAuth-specific reasons.
403	Forbidden	Agent lacks authority for requested action per Authority-Scope
404	Not Found	The path is absent from this server. No endpoints are registered under it.
405	Method Not Allowed	The method is recognized and the path is valid, but the server's policy or registry exposes no endpoint at that combination. The response body MUST list allowed methods for the path and any redirects from the manifest's `policies.methods` sub-block. The agent MAY PROPOSE the combination when policy is the only obstacle. AGTP-specific. See ; PROPOSE per .
408	Timeout	TTL exceeded before method could execute. AGTP-specific semantics; see below.
409	Conflict	Method conflicts with current state
410	Gone	Agent has been REVOKEd; canonical Agent-ID is permanently retired (status `retired`). A Deprecated agent (status `deprecated`) does NOT return 410 and continues to serve traffic; deprecation signals planned end-of-life while the agent remains in service. AGTP-specific semantics; see below.
422	Unprocessable	Request well-formed but semantically invalid
429	Rate Limited	Agent is exceeding permitted request frequency
455	Scope Violation	The request exceeds authority the agent holds: a claimed Authority-Scope beyond the identity document's grant (`scope-claim-invalid`), an endpoint whose required scope the agent's document omits (`scope-exceeded`), a DELEGATE granting more than the delegator's effective scope (`scope-exceeds-parent`), or a token- or query-defined scope dimension outside the standard set. Budget, rate, and zone have dedicated codes 456, 429, 457. AGTP-specific.
456	Budget Exceeded	Method execution would exceed the Budget-Limit declared in the request. AGTP-specific.
457	Zone Violation	Request would route outside the AGTP-Zone-ID boundary. SEP-enforced. AGTP-specific.
458	Counterparty Unverified	PURCHASE counterparty failed merchant identity verification: Merchant-ID absent, Merchant-Manifest-Fingerprint mismatch, or merchant in non-Active lifecycle state. AGTP-specific. See .
459	Method Violation	The method name is absent from the AGTP-METHODS approved method catalog. The method itself is the problem. AGTP-specific. See .
460	Endpoint Violation	The endpoint path violates AGTP-METHODS path grammar. A path segment matches an approved method name, indicating method-name leakage into the path. AGTP-specific. See .
461	RCNS Contract Available	The requested endpoint is unregistered but the server is prepared to synthesize a contract for it. The response body carries a contract preview the caller may accept or decline. Returned in the confirm-first RCNS delivery mode. AGTP-specific. See .
462	Insufficient Budget	Commerce request budget envelope is insufficient for the receiving agent's pricing tier or settlement requirements. AGTP-specific. See .
463	Proposal Rejected	The service cannot or declines to instantiate the proposed endpoint. Returned in response to PROPOSE. Response body MUST carry a structured reason (e.g., `out-of-scope`, `policy-refused`, `composition-impossible`, `ambiguous`, `synthesis-disabled`) and MAY carry an optional counter-proposal. AGTP-specific. See .
464	RCNS No Contract	An RCNS synthesis attempt was made but no contract could be delivered. Response body MUST carry a structured reason: `rcns-disabled` (RCNS policy off on this server), `trust-tier-insufficient` (caller's resolved trust tier is below the server's RCNS minimum), `composition-impossible` (no synthesis path exists from registered primitives), `synthesis-error` (synthesis attempt failed at runtime), `contract-not-yours` (presented `synthesis_id` was issued to a different agent), or `contract-revoked` (presented `synthesis_id` was revoked). AGTP-specific. See .
465	Reserved	Reserved for AGTP expansion.
500	Server Error	Internal failure in the responding system
503	Unavailable	Responding agent or system temporarily unavailable or Suspended
550	Delegation Failure	A delegated sub-agent failed to complete the requested action. AGTP-specific.
551	Authority Chain Broken	The Delegation Sequence cannot be verified: a hop fails parent re-verification, a hop's scope exceeds its parent's, the sequence exceeds the depth limit or contains a cycle, a member is in a non-Active lifecycle state, or the sequence has expired. The `reason` token names which (). AGTP-specific.
552	Reserved	Reserved for AGTP expansion.
553	Reserved	Reserved for AGTP expansion.
554	Reserved	Reserved for AGTP expansion.
555	Reserved	Reserved for AGTP expansion.

The four structural rejection codes (404, 405, 459, 460) form the contract-level structural failure surface and have distinct recovery semantics. A 459 tells the agent to choose a different method from the AGTP-METHODS catalog. A 460 tells the agent to restructure the path so that no path segment is a method name. A 405 tells the agent the method and path are each individually valid but the failure is a server policy decision; a different method-and-path combination might work, or PROPOSE might negotiate access. A 404 tells the agent the path is absent from this server altogether. Beyond the structural surface, 463 (Proposal Rejected) is the runtime negotiation rejection: the agent's PROPOSE was structurally valid but the server cannot or declines to synthesize the requested endpoint. Status code 262 (Authorization Required) consolidates the authority-related rejection conditions an agent might encounter when interacting with a server. It is returned when: (a) a PROPOSE request requires credential establishment before the server will evaluate it; (b) an endpoint invocation requires Authority-Scope that the agent has yet to declare; (c) an ad-hoc method invocation requires wildcards consent (wildcards: true on the agent identity document and wildcards_accepted: true in server policy) that is absent on either side; or (d) a discovery request is blocked by server policy that requires authenticated identity for manifest retrieval. The response body MUST identify which condition applies so the agent knows what to remediate. The rule separating 262 from 455 is obtainability. 262 Authorization Required is returned when the authorization the request lacks is one the agent could obtain without exceeding what it holds: a credential it has yet to establish, a consent it has yet to give or receive, or a scope its identity document grants but the request omitted from its claim. 455 Scope Violation is returned when the request exceeds the authority the agent holds: a claimed scope beyond the document's grant, an endpoint requiring a scope the document omits, or a delegation granting more than the delegator's effective scope. Earlier revisions used both codes for Authority-Scope failures in different sections; this revision applies the rule above throughout. 455 also covers operator-defined scope dimensions outside the standard set. Status code 456 (Budget Exceeded) is the dedicated code for resource-consumption scope violations: the agent's requested action would consume resources beyond what the principal authorized for this invocation. Status code 457 (Zone Violation) is returned by SEPs when a DELEGATE request would route to an agent outside the declared zone boundary. Status code 458 (Counterparty Unverified) is returned on PURCHASE invocations when the receiving server cannot verify that the requesting agent has performed valid merchant identity verification against the server's current Merchant Manifest Document, or when the merchant is in a non-Active lifecycle state; see . Status code 551 (Authority Chain Broken) is returned when a server processing a delegated request cannot verify the Delegation Sequence carried in the Delegation-Chain header per . The response body MUST carry the reason token and SHOULD identify the failing hop. Status code 408 (Timeout) is reused from HTTP with AGTP-specific semantics: it signals that the method's declared TTL expired before execution completed, distinct from HTTP's request-timeout semantics. Status code 410 (Gone) is reused from HTTP with AGTP-specific semantics: it indicates that an Agent-ID has been permanently retired through REVOKE of its Agent Genesis, distinct from HTTP's resource-removed semantics. A Deprecated agent does NOT return 410; deprecation signals planned end-of-life while the agent continues to serve traffic (see DEPRECATE in ). The canonical Agent-ID of a retired agent MUST NOT be retried. All AGTP-specific status codes are operational signals, distinct from protocol errors, and MUST be logged for audit purposes.

Structured Failure Fields A status code names the failure class. Agents retrying, resuming, or reporting a failure need three more facts: whether the request can be retried as sent, whether any of it completed, and whether it left side effects. Every 4xx and 5xx response body SHOULD carry the following fields, and servers that implement or any action method MUST carry them:

retryable:: true when the identical request MAY be re-sent without further change; false when the request must change first (different scope, a corrected body, a new proposal); unknown when the server cannot determine this.
partial:: true when part of a multi-step invocation completed before the failure. When true, completed_steps carries the ordered list of step identifiers that completed, so a caller can resume from the first incomplete step.
side_effects:: none when the failed request changed no state; committed when it changed state that persists despite the failure; unknown when the server cannot determine this. Action methods ( defines the property) MUST NOT report none unless the server verified it.
evaluation:: refused when the server evaluated the request and decided against it; incomplete when a check the decision depends on was unable to run. When incomplete, missing_input names the input that was unavailable (an unreachable registry, an expired credential, a log that failed to answer). An intermediary that forwards a response MUST NOT convert incomplete into refused; an intermediary that narrows a request is a decision point and records its own evaluation. A refusal and an incomplete check are different outcomes and are never collapsed.
reason:: A token from the vocabulary registered for the status code, as already required for 262, 455, 463, 464, and 551.

The fields are additive and wire-compatible: a v09 client ignores them; a v09 server omits them. They answer the typed-error question raised in review without changing any status code.

Wire Format and Content-Type AGTP request and response bodies are encoded as JSON or YAML. The following media types are defined by AGTP. Their IANA registration status varies; see the IANA Considerations section for the authoritative status table. AGTP Media Types Defined in This Document

Media Type	Use	IANA Status
`application/vnd.agtp+json`	AGTP method request/response bodies (JSON)	Planned (this document)
`application/vnd.agtp+yaml`	AGTP method request/response bodies (YAML)	Planned (this document)
`application/vnd.agtp.identity+json`	Agent Identity Document (JSON)	Registered (vendor tree)
`application/vnd.agtp.identity+yaml`	Agent Identity Document (YAML)	Registered (vendor tree)

Two additional media types are defined in the companion AGTP-METHODS specification and registered concurrently: application/vnd.agtp.manifest+json (server manifest) and application/vnd.agtp.endpoint+json (endpoint definition). Both are listed in the master Media Type Registry section of this document for cross-document discoverability. Implementations MUST include the appropriate Content-Type on all AGTP requests and responses that carry a message body. Responses with no body (e.g., 204 No Content) MUST NOT include a Content-Type header. Binary or streaming extensions MAY define additional Content-Type values as part of their companion specifications. EXECUTE method invocations carry application-layer payloads whose Content-Type is set by the carried application protocol (for example, application/vnd.mcp.tools+json for MCP tool invocations carried over AGTP). The AGTP server dispatches based on the carried Content-Type; see and . The common structure for AGTP method-level request bodies: And for AGTP method-level response bodies:

Early Implementations AGTP is a proposed specification. No production implementations exist at the time of this writing. The author encourages early prototype implementations to validate the protocol design, identify gaps, and generate feedback prior to IETF working group submission.

If you are building an AGTP prototype or reference implementation, please share your findings via the feedback channel listed on the cover of this document. A reference implementation in Python and/or Go is planned as open-source software concurrent with or shortly after IETF I-D submission. Implementation reports are welcome and will be incorporated into subsequent draft revisions.

Implementers wishing to experiment before final IANA port assignment SHOULD use a locally-chosen port from the Dynamic Ports range (49152-65535) on developer-controlled endpoints. Implementations MUST NOT publish or document any specific port number as an AGTP-associated value until IANA assignment is complete. ACTIVATE is one of the three Lifecycle methods on the eighteen-method floor; see . Earlier revisions of this document described ACTIVATE as an optional method extension carried in a separate companion. With the promotion of the Lifecycle group to the embedded floor, ACTIVATE, DEACTIVATE, and REVOKE are all core methods; any conformant AGTP implementation MUST support them. Package-binding semantics specific to .nomo governed packages remain governance-platform-specific and MAY be layered on top of the protocol-level ACTIVATE transaction without affecting the wire contract.

Agent Identity, URI Structure, and Registration

URI Structure and Resolution Mechanics

Foundational Principle AGTP identity is agent-first. Every agent is identified by a canonical Agent-ID: a 256-bit cryptographic identifier derived from the agent's Agent Genesis hash at registration. The canonical Agent-ID is the authoritative identifier in every AGTP protocol operation. It appears in the Agent-ID header of every request, is the key in the registry, and is the cross-layer reference linking the AGTP Agent Certificate extension to the governance-layer Agent Genesis. All other agent identification forms recognized by AGTP, including domain-anchored URIs and Web3 resolution targets, are aliases that resolve to a canonical Agent-ID. In the event of any conflict between an alias and a canonical Agent-ID, the canonical Agent-ID MUST be treated as authoritative. AGTP URIs are addresses. File format suffixes (.agtp) MUST NOT appear in canonical agtp:// URIs. A URI resolves to an Agent Identity Document or Agent Namespace Document derived from the underlying package; it never exposes or serves the package itself. Implementations MUST treat any URI containing a file extension in the path as non-canonical and SHOULD issue a 301 Moved Permanently redirect to the canonical form prior to resolution. The .agent suffix and the .nomo suffix are file format designators for AGTP agent packages; they are never URI hostname labels. Earlier drafts admitted hostname forms ending in .agent or .nomo as agent-native hierarchical TLDs; this revision removes that admission. Hostnames in AGTP URIs are standard DNS hostnames per RFC 3986.

Canonical URI Forms AGTP is identity-first. Agent-IDs are canonical and content-addressed; hosting is incidental. Form 1 (agtp://[Agent-ID]) is the canonical identity form. Form 1a (agtp://[Agent-ID]@[host]) provides direct addressing for cases where the resolver has yet to learn how to reach the canonical ID, and bridges the gap between identity-first addressing and the existing DNS-based reachability infrastructure. Forms 2 and 2a address servers and organizations, with no specific agent named, providing entry points for discovery operations that target no named agent. Forms 3 and 4 address agents by local name within a domain's namespace; they differ only in deployment convention. The port portion of any AGTP URI is OPTIONAL. When omitted, AGTP clients MUST use the IANA-assigned default port 4480. The port is included in URIs only for non-default deployments and appears in the host component (Form 1a host or Form 2 host); ports MUST NOT appear in Form 2a domain components or in Forms 3/4 domain components.

Form 1: Canonical Identity Form 1 carries only the 64-character lowercase hex representation of the Agent Genesis SHA-256 hash: Form 1 resolves to a signed Agent Identity Document through any verification path declared in the agent's registry record (Section 5.2). The canonical ID is self-describing: any AGTP-aware governance platform, transparency log, or resolution service can return the Identity Document given the canonical ID alone, without prior knowledge of which organization, domain, or blockchain the agent is registered under.

Form 1a: Canonical Identity with Explicit Host Form 1a embeds an explicit host alongside the canonical Agent-ID: The Agent-ID identifies; the host tells the resolver where to reach a server that can return the Identity Document or accept method invocations. Form 1a is the preferred form when:

The agent has been issued a canonical Agent-ID but is yet to be registered with an AGTP discovery service.
The resolver has yet to acquire a path from canonical Agent-ID to endpoint (no DNS anchor, no transparency log entry, no governance-platform resolution).
A client wishes to address an agent by ID directly without round- tripping through a registry.

Form 1a leaves the identity-first model intact. The canonical Agent-ID remains authoritative; the host portion is treated as a resolution hint and MUST NOT be used to derive identity. If the host returns an Identity Document whose agent_id field fails to match the canonical Agent-ID in the URI, the response MUST be rejected.

Form 2: Server-Level Discovery Form 2 addresses a specific server endpoint without naming an agent: The host component MAY be any RFC 3986 host: a registered hostname, an FQDN, an IPv4 address, an IPv6 address, optionally followed by a port. Form 2 is used for diagnostic operations addressing a specific server instance (a particular edge node, a specific deployment in a load-balanced fleet, a server identified by IP) and for method invocations that target server-level state as distinct from agent-level state.

Form 2a: Organization-Level Discovery Form 2a addresses an organization's AGTP presence via its registered DNS domain: The domain component MUST be a DNS-registered domain name with at least one label. IP addresses, ports, and userinfo components MUST NOT appear in Form 2a; URIs carrying any of these are Form 2. Form 2a resolution proceeds via standard DNS lookup of the domain, then AGTP connection establishment on port 4480 against the resolved address. The response is the organization's canonical server manifest. Whether the domain resolves to a single AGTP server, a load-balanced fleet, or a CDN-fronted edge is a deployment concern; Form 2a commits the caller to no specific topology. The syntactic distinction between Form 2 (any RFC 3986 host, possibly with port) and Form 2a (bare DNS domain) corresponds to a semantic distinction. Form 2 addresses a specific reachable server; Form 2a addresses whichever server the organization's DNS currently points at. Both forms are valid; a caller chooses by whether it means that server or whichever server the organization designates.

Forms 3 and 4: Domain-Anchored Agents Forms 3 and 4 address an agent by local name within a domain's agent namespace: Form 3 places the agent under the organization's primary domain. Form 4 places the agent under a dedicated agtp. subdomain. Resolution semantics are identical: the AGTP server at the domain (or subdomain) consults its hosted_agents manifest entries and returns the canonical Agent-ID for the named local agent. The local agent name is unique within the domain's namespace; the same name under a different domain is a different agent. Forms 3 and 4 differ only in deployment convention. Operators choose based on their infrastructure preferences: organizations that prefer to keep agent-protocol traffic on a dedicated subdomain use Form 4; organizations that operate AGTP as the canonical face of their primary domain use Form 3. The protocol treats them as equivalent. In both forms the domain component MUST be a DNS-registered domain name; IPs and ports MUST NOT appear. Direct addressing with explicit host is available via Form 1a if the resolver knows the canonical Agent-ID.

URI Grammar The URI grammar is defined in ABNF as: AGTP URIs are addresses. File extensions in the path MUST NOT appear in canonical agtp:// URIs. A URI resolves to an Agent Identity Document, a server manifest, or an endpoint response derived from server state; it never exposes or serve a package file. Implementations MUST treat any URI containing a file extension in the path as non-canonical and SHOULD issue a 301 Moved Permanently redirect to the canonical form prior to resolution.

Method-on-URI Invocation Pattern AGTP method invocations target a URI plus an optional endpoint path. The conceptual pattern is: The locator addresses an agent (Forms 1, 1a, 3, 4), a server (Form 2), or an organization (Form 2a). The endpoint path is the path portion of the request line as specified in . For server-level and organization-level discovery operations the endpoint path is omitted (target-less DISCOVER); for agent-level operations the endpoint path identifies the endpoint to invoke. The wire-level encoding of this pattern is the AGTP request line (method and path) plus the connection target (host derived from the URI). The URI is the agent-facing addressing notation; the wire format travels over TLS.

Web3 Verification Anchors AGTP supports Web3-anchored verification paths for canonical Agent-IDs whose underlying Agent Genesis is registered through a blockchain-based verification service. The verification path is declared in the agent's registry record per ; URI syntax is the same for every path: a Web3-anchored agent is addressed by its canonical Agent-ID via Form 1 or Form 1a like any other agent. Integration with specific Web3 naming and resolution systems is outside this document; the earlier Web3 bridge draft is withdrawn and any future binding will be a companion specification.

Non-Canonical Forms and Redirect Behavior The following non-canonical forms SHOULD be redirected to their canonical equivalents. Implementations MUST NOT serve package contents in response to any URI form. Non-Canonical URI Forms and Redirect Targets

Received URI	Canonical Redirect Target
`agtp://acme.tld/agents/customer-service.agent`	`agtp://acme.tld/agents/customer-service`
`agtp://acme.tld/agents/customer-service.nomo`	`agtp://acme.tld/agents/customer-service`
`agtp://acme.tld/agents/customer-service.agtp`	`agtp://acme.tld/agents/customer-service`

Query Parameters for Format Selection All AGTP URI resolution requests accept an optional format query parameter controlling the serialization of the returned document. AGTP URI Format Query Parameters

Query Parameter	Returned Representation
(none)	Agent Identity Document, human-readable `application/vnd.agtp+json`
`?format=manifest`	Agent Identity Document, human-readable `application/vnd.agtp+json`
`?format=json`	Agent Identity Document, compact `application/vnd.agtp+json`
`?format=certificate`	Agent Genesis fields only, `application/vnd.agtp+json`
`?format=status`	Lifecycle state and operational status only, `application/vnd.agtp+json`

All format variants return signed application/vnd.agtp+json content. The ?format=json parameter is intended for programmatic consumers. The default returns the full human-readable manifest suitable for browser rendering by an AGTP-aware client.

Resolution Mechanics AGTP URI resolution proceeds according to the URI form presented. Form 1 and Form 1a (canonical agent identity) resolve through a governance-platform registry or transparency-log lookup. Forms 2 and 2a (server and organization discovery) resolve through direct AGTP connection establishment to the host or domain. Forms 3 and 4 (domain-anchored agents) resolve through DNS to an AGTP server whose hosted_agents manifest maps the URI's local agent name to a canonical Agent-ID.

Form 1 Resolution (Canonical ID) When an AGTP resolver receives a URI of the form agtp://[256-bit-hex-id], it MUST perform the following steps:

Parse and validate the canonical Agent-ID. If the identifier is malformed (length, character set), return 400 Bad Request with error code invalid-canonical-id.
Query the agent's governance platform registry for the record associated with the canonical Agent-ID. If the resolver fails to know which governance platform holds the record, it MAY query a transparency log per to locate the record.
Verify the registry record lifecycle state. If suspended, return 503 Service Unavailable with lifecycle state in the response body. If retired, return 410 Gone with lifecycle state and revocation timestamp. If deprecated, the resolver SHOULD continue with resolution; the registry record MUST carry the deprecation signal so the relying party can surface it to clients and act on any successor_agent_id declared in the deprecation event.
Retrieve the agent's package (.agent or .nomo) from the package store referenced by the registry record.
Verify the package integrity hash before proceeding. If integrity verification fails, return 500 Internal Error with error code package-integrity-failure. MUST be logged.
Extract the embedded manifest from the verified package.
Sign the Identity Document using the governance platform's signing key. Return the signed application/vnd.agtp+json document in the format specified by the query parameter.

Form 1 resolution requires no prior knowledge of an organization domain, a DNS record, or a Web3 naming anchor; the canonical Agent-ID is the only input.

Forms 2 and 2a Resolution (Server and Organization Discovery) When an AGTP resolver receives a URI of Form 2 (agtp://[host]) or Form 2a (agtp://[domain]), it MUST perform the following steps:

Parse and validate the URI. Form 2 admits any RFC 3986 host with optional port. Form 2a admits a DNS-registered domain name with at least one label and MUST NOT include port or userinfo components.
Open an AGTP/TLS connection to the host or domain. For Form 2a, resolve the domain via DNS first. For both forms, AGTP traffic targets port 4480 unless an explicit non-default port appears in the URI (Form 2 only).
Issue the agent's intended method (typically DISCOVER for discovery operations) with no agent-identifying target.
The server returns its server manifest (for Form 2 or Form 2a addressed against a server's primary endpoint) or whatever server-level response the invoked method produces.

Forms 2 and 2a resolve to no canonical Agent-ID; they target server or organization state directly. They take no part in the canonical-Agent-ID identity model.

Forms 3 and 4 Resolution (Domain-Anchored Agents) When an AGTP resolver receives a URI of Form 3 or Form 4, it MUST perform the following steps:

Parse and validate the URI. If the URI is malformed, return 400 Bad Request with error code invalid-uri-form.
Resolve the domain (Form 3) or agtp.[domain] subdomain (Form 4) via DNS, then open an AGTP/TLS connection to port 4480.
Look up the agent-name from the URI path against the server's hosted_agents manifest entries to obtain the canonical Agent-ID. If no matching agent is found, return 404 Not Found.
Continue with Form 1 resolution steps 3 through 7 using the resolved canonical Agent-ID.

The package's executable content, code, logic, and any fields absent from included in the Identity Document schema MUST NOT be returned at any step of any resolution path. URI resolution exposes identity and status exclusively.

Trust Tiers and Verification Paths The Agent Genesis carries a trust_tier field (one of 1 Verified, 2 Org-Asserted, 3 Experimental) and a verification_path field (one of dns-anchored, log-anchored, hybrid, or org-asserted) recording how the agent's identity was anchored at registration. These fields are surfaced in the Agent Identity Document and consulted by Scope-Enforcement Points, governance gateways, and peer agents during runtime authority decisions. Tier 1 agents are eligible for the full Authority-Scope vocabulary, delegation chains, financial transactions, and multi-organization collaboration. Tier 1 verification requires exactly one of three verification paths (dns-anchored, log-anchored, hybrid) to succeed at registration, before ACTIVATE, each backed by distinct evidence (DNS TXT record, transparency log inclusion proof, or DNS + blockchain signature combination). All Tier 1 paths produce identity attestations of equivalent strength. Tier 2 agents declare organizational affiliation without cryptographic verification (verification_path: org-asserted) and carry the trust_warning: "verification-incomplete" signal. Tier 3 agents are experimental and confined to development environments. The normative verification procedures, evidence requirements, tier assignment rules, and Authority-Scope eligibility constraints are specified in .

Subdomain Deployment Pattern Organizations SHOULD deploy AGTP endpoints at a dedicated subdomain following the pattern agtp.[organization-domain.tld] (e.g., agtp.acme.tld). This is the recommended enterprise deployment pattern: it provides clean separation between web and agent infrastructure, allows independent certificate management for the AGTP endpoint, and is consistent with service-specific subdomain conventions. An organization with an AGTP subdomain SHOULD also configure their primary domain to redirect AGTP requests:

The /agents/ Reserved Path Prefix The path prefix /agents/ is reserved in all agtp:// URIs for agent namespace operations. Implementations MUST support this prefix. The registry root at /agents (no trailing label) resolves to the Agent Namespace Document ().

Collision Prevention The canonical Agent-ID is the collision-prevention primitive. Two canonical Agent-IDs are distinct if and only if the 256-bit identifiers differ, and the governance platform enforces uniqueness at issuance time by deriving the ID from the Agent Genesis hash. For alias forms, collision prevention operates at the namespace level. agtp://acme.com/agents/customer-service and agtp://chrishood.com/agents/customer-service resolve to distinct canonical Agent-IDs because they are registered under different DNS domains. Within a single governance zone, the governance platform enforces uniqueness of agent local names at registration time. Infrastructure MUST use the canonical Agent-ID for all routing, logging, and attribution operations. Alias URIs are a display and discovery layer only. An alias that resolves to a canonical Agent-ID different from the one carried in the Agent-ID header on a request MUST cause the request to be rejected with 401 Unauthorized and MUST be logged.

IANA Considerations for the agtp:// URI Scheme The agtp:// URI scheme is registered with IANA per . Registration template:

URI scheme name:: agtp
Status:: Permanent
URI scheme syntax:: agtp://[Agent-ID] (canonical identity, Form 1) agtp://[Agent-ID]@[host] (canonical identity with explicit host, Form 1a) agtp://[host] (server-level discovery, Form 2) agtp://[domain] (organization-level discovery, Form 2a) agtp://[domain]/agents/[agent-name] (domain-anchored agent, Form 3) agtp://agtp.[domain]/agents/[agent-name] (subdomain-anchored agent, Form 4)
URI scheme semantics:: Identifies an AI agent, an AGTP server, or an organizational AGTP presence operating over the Agent Transfer Protocol. The authoritative agent identification form (Form 1) uses a 256-bit hex-encoded cryptographic identifier derived from the agent's Agent Genesis. Form 1a augments the canonical ID with an explicit host to enable direct addressing in deployments where the canonical ID has yet to be resolved through a registry. Forms 2 and 2a address servers and organizations respectively for discovery operations that target no specific agent. Forms 3 and 4 address agents by local name within a domain's namespace and resolve to canonical Agent-IDs through the server's hosted_agents manifest. Forms 3 and 4 differ only in deployment convention.
Applications/protocols that use this URI scheme:: Agent Transfer Protocol (this document)
Interoperability considerations:: The canonical Agent-ID form is the authoritative agent identity representation. Form 1a embeds a resolution hint alongside the canonical Agent-ID and MUST NOT be used to derive identity. Forms 3 and 4 resolve through DNS to an AGTP server endpoint whose hosted_agents manifest maps the URI path component to a canonical Agent-ID. Forms 2 and 2a resolve to no canonical Agent-IDs; they target server or organization state directly. Implementations MUST accept canonical Agent-IDs (Form 1) and SHOULD support at least one of the domain-anchored agent forms (Form 3 or Form 4). The port portion of any AGTP URI is OPTIONAL and defaults to the IANA-assigned port 4480 when omitted; ports MAY appear in Form 1a and Form 2 only. File format suffixes (.agtp, .agent, .nomo) MUST NOT appear in agtp:// URIs.
Contact:: Chris Hood, chris@nomotic.ai
References:: This document

The agtp:// URI scheme registration is open and unencumbered. No intellectual property claims apply to the URI scheme itself.

.well-known Bootstrap Organizations operating an AGTP namespace under a DNS domain SHOULD publish a bootstrap document at the well-known URI https://{domain}/.well-known/agtp per . The document is returned over HTTPS and declares the organization's AGTP presence, the endpoint at which AGTP traffic should be directed, and any verification anchors the organization wishes to surface for discovery. The bootstrap document is JSON with the following fields: Resolvers encountering an agtp:// URI for a domain they have had no previous interaction with SHOULD retrieve the bootstrap document to learn the canonical AGTP endpoint and verification anchors before attempting AGTP traffic. The bootstrap is advisory; absence of a .well-known/agtp document is no indication that the domain has no AGTP presence, only that the domain has chosen against advertising one through this mechanism. A .well-known/agtp document returning HTTP 404 is a positive declaration that the domain operates no AGTP namespace. Resolvers MAY cache this negative result for the period indicated by the HTTP response's Cache-Control directive, with a default of 24 hours when no directive is present.

Agent Identity Document (Summary) Every Canonical Agent-ID resolves to an Agent Identity Document: a signed application/vnd.agtp.identity+json document that carries the agent's Owner-ID, its declared Authority-Scope set, its trust posture fields, its supported methods and content types, and the issuer binding that makes the document tamper-evident. The Agent Namespace Document, the .agtp package format, the human-readable identity view served to browsers, and the status sub-resource are specified in . This document carries only what the protocol depends on:

The document is the authority for the Owner-ID (which MAY be a Legal Entity Identifier bound per ) and the full Authority-Scope set; a request's claimed Authority-Scope is validated as a subset of it ().
The document is signed, and the signature is verified before any field is trusted ( specifies the integrity and freshness rules). When the optional issuer fields are absent the document is verifiable at Level 1 only ( supplies Level 3).
Resolution of an Agent-ID to its document follows ; the media types are registered in .

Agent Registration Process

Overview An agent cannot participate in AGTP until it has been issued an Agent Genesis by a governance platform and assigned a canonical Agent-ID derived from that document. Canonical Agent-IDs are issued at registration, when the Genesis is signed; they are never self-declared, and ACTIVATE () is the later lifecycle transition that makes an already-issued Agent-ID reachable. The Agent Genesis is the genesis record of an agent's legal existence within the AGTP ecosystem. Its relationship to the canonical Agent-ID is analogous to the relationship between a government-issued birth registration and a social security number: the birth event produces a permanent, authoritative identity record, and a durable identifier is derived from it. The identifier follows the agent for its entire lifecycle, including after revocation. It is never reissued to another agent. Any AGTP infrastructure component MUST reject requests carrying an Agent-ID that fails to resolve to an Agent Genesis record in an Active lifecycle state in a reachable registry.

Agent Genesis Contents The Agent Genesis is issued by the governance platform at registration and contains the following fields: Agent Genesis Fields

Field	Required	Description
`agent_id`	MUST	Canonical Agent-ID for this agent. Equals the 256-bit SHA-256 hash of the Agent Genesis in its canonical-form serialization with the `signature` and `log_inclusion_proof` fields excluded. Excluding the inclusion proof lets the issuer compute the Agent-ID, commit it to the transparency log, and embed the resulting receipt without changing the identity (). The field is included for relying-party convenience; verifiers MUST independently recompute the hash and confirm it matches before trusting the value.
`owner`	MUST	Human or team responsible for this agent
`archetype`	MUST	Behavioral category (see archetypes below)
`governance_zone`	MUST	Environment context (development, staging, production)
`scope`	MUST	Authorized action types
`issued_at`	MUST	Timestamp of issuance
`issuer_public_key`	MUST	Ed25519 public key of the governance platform (or self-issuer in development) that signed this Agent Genesis. 32 raw bytes encoded as base64url. Verifiers re-verify `signature` against this key. The SHA-256 fingerprint of these raw bytes is the Genesis-issuer fingerprint used for lifecycle-method authorization ().
`signature`	MUST	Detached Ed25519 signature over the canonical-form serialization (with the `signature` field excluded), produced by `issuer_public_key`'s corresponding private key. Self-signed Agent Genesis records (where `issuer_public_key` is the agent's own key) are permitted for development; production deployments MUST use a recognized issuer key.
`package_ref`	SHOULD	Reference to the `.agent` or `.nomo` package
`trust_tier`	MUST	Registration tier (1, 2, or 3)
`verification_path`	MUST (Tier 1)	Path used to verify identity: `dns-anchored`, `log-anchored`, `hybrid`, or `org-asserted`
`org_domain`	SHOULD	DNS-verified or asserted org domain (required for `dns-anchored` and `hybrid`)
`org_label`	SHOULD	Agent-native org label (required for Form 2 hierarchical resolution)
`log_inclusion_proof`	MUST (log-anchored)	Transparency log inclusion proof (RFC 9162 / RFC 9943)
`log_uri`	MUST (log-anchored)	Absolute HTTPS URI of the base of the transparency log's protocol surface, at which the inclusion proof and signed tree head are retrievable per

The canonical-form serialization used for both the Agent-ID hash and the signature MUST be deterministic: keys sorted lexicographically, no insignificant whitespace, UTF-8 encoding, and the signature field omitted from the serialized form. Implementations MUST produce identical bytes for the same logical Agent Genesis across implementations.

Agent Archetypes The archetype field classifies the agent's behavioral category. Archetypes inform scope enforcement and observability tooling; an executor archetype agent exhibiting read-only query patterns, or a monitor archetype agent attempting booking operations, are anomaly signals. The archetype field plays no part in scope enforcement; Authority-Scope headers govern actual permissions at the protocol level. Archetypes are a classification and observability signal; the security boundary is Authority-Scope. Agent Archetypes

Archetype	Description	Typical Scope
`assistant`	Conversational agent, read-heavy	`documents:query`, `knowledge:query`
`analyst`	Data analysis, read and aggregate	`data:read`, `data:aggregate`
`executor`	Takes real-world actions, write-heavy	`booking:*`, `payments:confirm`
`orchestrator`	Manages other agents	`delegation:`, `agents:`
`monitor`	Observational only	`telemetry:read`, `logs:read`

Agent Genesis to AGTP Protocol Mapping Agent Genesis fields map to AGTP protocol elements that surface during request processing. This mapping is the mechanism by which static identity (the Agent Genesis) becomes runtime identity (the protocol session): Agent Genesis to AGTP Protocol Mapping

Agent Genesis Field	AGTP Protocol Element
`agent_id`	`Agent-ID` header on every request
`owner`	Principal identifier in the agent identity document; never transmitted as a separate header
`scope`	Full Authority-Scope set in the agent identity document; optionally narrowed per-request via the `Authority-Scope` header
Canonical Agent Genesis (full document)	Hashed to produce the canonical Agent-ID; the document itself is the identity anchor

The canonical Agent-ID is computed as sha256(canonical_form(Agent_Genesis_without_signature)). The chain (Agent Genesis document to canonical hash to Agent-ID header) ensures that the identifier carried in the Agent-ID header on every AGTP request is traceable back to the original Agent Genesis and the human principal who authorized the agent's creation. Any modification to the Agent Genesis produces a different canonical Agent-ID; tampering is therefore detectable by any verifier that recomputes the hash.

Registration Tiers Registration produces an Agent Genesis at one of three trust tiers (Tier 1 Verified, Tier 2 Org-Asserted, Tier 3 Experimental). Tier 1 registration requires one of three verification paths (dns-anchored, log-anchored, hybrid) to succeed at ACTIVATE time, each backed by distinct cryptographic evidence. Tier 2 registration declares organizational affiliation without cryptographic proof; the resulting Agent Genesis carries trust_warning: "verification-incomplete". Tier 3 registration is confined to development environments and produces a locally-scoped Agent Genesis. The complete tier-specific packaging, evidence, and validation requirements are specified in .

Registration Lifecycle

AGTP Agent Registration Lifecycle

Contract-Related Lifecycle Events In addition to the five agent-state lifecycle events above, AGTP servers that operate the Runtime Contract Negotiation Substrate () emit three contract-related events on the per-agent lifecycle stream of the contract's originating agent. The events ride the same signed-envelope lifecycle stream described in and are retrievable via INSPECT target=lifecycle; they are stored outside any separate audit surface. RCNS Contract-Related Lifecycle Events

Event Type	Triggered By	Subject
`rcns_propose_accepted`	A synthesized contract is instantiated, whether through the RCNS gate or an explicit PROPOSE	Originating Agent-ID; payload carries `synthesis_id`, `(method, path)`, recipe lineage, and `negotiation_origin`
`rcns_revoke`	`REVOKE target=contract` invocation per	Originating Agent-ID; payload carries the revoked `synthesis_id` and operator-supplied reason
`rcns_release`	`SUSPEND synthesis_id=...` invocation per , or `REVOKE target=stale-contracts` invocation per when a drifted contract is evicted	Originating Agent-ID; payload carries the released `synthesis_id`. For agent-initiated release the reason is agent-supplied; for operator-fired stale-contract eviction the reason MUST be `policy-change-invalidation` and the operator's identifier MUST be recorded so audit consumers can distinguish operator-fired invalidations from agent self-releases

The three RCNS event types are reserved on the Agent Identity Document lifecycle stream alongside the five agent-state events. They are absent from the AGTP-LOG transparency log statement vocabulary defined in ; transparency-log submission of contract events, if any, is left to a future revision.

Governance Tokens and Runtime Authorization Following successful registration, the agent's Agent Genesis is the static identity anchor. Runtime authorization for specific actions is carried by Governance Tokens: signed, time-limited JWT artifacts issued by the governance platform encoding a specific governance verdict (ALLOW, DENY) for a specific action. Governance Tokens MUST NOT be reused. Each action requires a fresh evaluation and a fresh token. Default TTL is 30 seconds. The token's agent_id field MUST match the canonical Agent-ID from the Agent Genesis. Tokens that fail this validation MUST be rejected and the failure MUST be logged. A Governance Token authorizes a specific action, and the verifier MUST be able to check that the action executed is the action authorized. Every Governance Token MUST carry action_digest: the SHA-256 of the canonical serialization of the object {method, path, action, parameters, payload_type, payload_sha256} drawn from the request the token authorizes, with absent members omitted. At dispatch the server recomputes the digest from the request as received and MUST reject with 262 Authorization Required and reason token-action-mismatch when the two differ, logging both digests. A token therefore binds to one request shape; a replay against a different path, parameter set, or payload fails the comparison before any handler runs. The relationship between Agent Genesis and Governance Token parallels the relationship between a passport and a visa: the passport establishes persistent identity; the visa encodes a specific time-bounded permission. Holding a passport implies no particular any particular visa.

Friendly Name Availability and Re-Registration An agent label becomes available for re-registration 90 days after its associated agent enters Revoked or Deprecated lifecycle state. The canonical Agent-ID and Agent Genesis are permanently archived. The canonical Agent-ID MUST NOT be reissued under any circumstances, including re-registration of the same label by the same organization. This policy prevents ID reuse attacks in which a newly registered agent inherits the trust history of a revoked predecessor.

Method Definitions

Design Philosophy AGTP methods are intent verbs. Each method expresses what an agent is trying to accomplish, where an HTTP method names an operation on a resource. Method names are uppercase ASCII strings. Methods that modify state are NOT idempotent by default unless explicitly marked. All methods accept a context parameter carrying agent session state. Requirement language follows .

The Sixteen-Method Floor AGTP defines eighteen protocol-level methods that constitute the embedded floor of the protocol. Any conformant AGTP implementation MUST support all eighteen. The eighteen are organized as three groups. Cognitive methods express requests for information or reasoning. A cognitive method invocation produces understanding without changing state external to the agent's own session:

QUERY: semantic data retrieval
DISCOVER: locate agents, resources, or services
DESCRIBE: retrieve operational capabilities of a known endpoint
INSPECT: retrieve audit records, chain heads, and lifecycle entries from the responding server
SUMMARIZE: synthesize provided content
PLAN: produce an unexecuted sequence of actions toward a goal
PROPOSE: submit a dynamic endpoint or method proposal

Mechanics methods perform actions, exercise authority, or change state. A mechanics method invocation has external effect:

EXECUTE: invoke a specific action or carried protocol payload
DELEGATE: transfer execution to a sub-agent with bounded authority
ESCALATE: route a decision to a higher authority or human principal
CONFIRM: attest to a prior action, state, or item
SUSPEND: pause an active session workflow with a resumption nonce
NOTIFY: push information without expectation of synchronous response

Lifecycle methods transition an agent between registry states. A lifecycle method invocation produces a signed lifecycle event in the per-agent lifecycle stream and updates the agent's registry status; it changes how the agent is treated by AGTP infrastructure but invokes no application-layer behavior:

ACTIVATE: transition an agent into the Active state, emit an activation event
DEACTIVATE: transition an agent out of Active (typically to Suspended), emit a deactivation event
REINSTATE: transition a Suspended agent back to Active, emit a reinstatement event
REVOKE: permanently retire an agent's canonical Agent-ID, emit a revocation event
DEPRECATE: transition an agent to Deprecated (controlled end-of-life; agent continues to accept traffic), emit a deprecation event

The cognitive/mechanics/lifecycle distinction is informational, informational; servers behave identically regardless of the category of a method. The classification provides a stable mental model for spec readers and implementers and constrains future additions to the floor. EXECUTE is the generic carrier for application-layer payloads. When a higher-level agent framework such as MCP, A2A, or ACP is composed over AGTP (see ), EXECUTE is the method that dispatches the carried payload to the application based on its Content-Type. EXECUTE absorbs the role that earlier drafts of this specification considered for an INVOKE method.

Core Methods The eighteen core methods are presented below in the cognitive group followed by the mechanics group, then the lifecycle group. The four methods present in v06 core that are absent from the v07 floor (BOOK, SCHEDULE, LEARN, COLLABORATE) are demoted to Tier 2 standard extended methods; their specifications continue to apply where implementations choose to support them, and they are catalogued in the AGTP-METHODS method catalog ().

QUERY Purpose: Semantic data retrieval. The agent specifies what it needs to know; where to find it is the server's problem. Distinguished from HTTP GET, which retrieves a known resource at a known location, by expressing an information need. Cognitive. QUERY Parameters

Parameter	Required	Description
intent	MUST	Natural language or structured expression of the information need
scope	SHOULD	Data domains or sources to include or exclude
format	MAY	Desired response format: structured, natural, raw
confidence_threshold	MAY	Minimum confidence score for included results (0.0-1.0)
context	MAY	Session context for disambiguation

Response: Result set with confidence scores per item. Server SHOULD indicate provenance of each result. Idempotent: Yes.

DISCOVER Purpose: Search for agents matching a capability need, or discover the current attachment of a known Agent-ID. Returns a ranked list of candidate Agent Identity Documents, each carrying the attachment at which the agent is currently reachable. Distinguished from QUERY: DISCOVER returns agents to talk to, QUERY returns data to consume. Cognitive. The two uses are distinguished by the vocabulary of following RFC 6763: a DISCOVER whose criteria describe a need (intent, capability domains, trust and governance constraints) is a search and returns candidates to be evaluated; a DISCOVER whose criteria name a single Agent-ID is a discovery and returns that agent's signed attachment. The parameter set, the response shape, the ranking rule, and the operational modes (direct Presence, ANS-brokered, cross-scope) are specified normatively in ; the population a search runs over is the presence substrate of . This document fixes only the floor: the method name, its safe and idempotent properties, the discovery:query scope requirement, and the governance-zone rule below. Servers MUST apply governance-zone filtering: candidates outside the requesting agent's permitted zones MUST NOT be returned. Every result MUST carry the agent's Canonical Agent-ID; a result with no Agent-ID is a search hit from an external catalog and MUST be marked as such. Idempotent: Yes. Primary error codes: 422, 455.

DESCRIBE Purpose: Return the operational capabilities of a known agent endpoint. The requesting agent specifies what capability dimensions it needs to evaluate; the server returns a structured Capability Document. Used for pre-task negotiation before committing to DELEGATE or EXECUTE. If capability_domains is omitted, the server SHOULD return all supported domains. Cognitive. DESCRIBE Parameters

Parameter	Required	Description
capability_domains	SHOULD	Comma-separated domains to return: `methods`, `modalities`, `tools`, `version`, `budget`, `zones`. If omitted, server SHOULD return all.
version_min	MAY	Minimum acceptable version for capability negotiation.
context	MAY	Session context for capability filtering.

Response: Capability Document with the following structure: Idempotent: Yes. Primary error codes: 404, 422.

INSPECT Purpose: Retrieve audit records, per-agent chain heads, or lifecycle log entries from the responding server's audit store. INSPECT is the read counterpart to the per-action Attribution-Record and per-agent audit chain established by the response path: a relying party that holds an Audit-ID can fetch the underlying JWS, walk the chain by following previous_audit_id, and verify the chain's integrity end-to-end. Cognitive. INSPECT Parameters

Parameter	Required	Description
target	MUST	Target family. One of `audit`, `chain_head`, `lifecycle`, `contract`, or `rcns-attempt`; the last two are the RCNS extensions whose semantics are in .
audit_id	CONDITIONAL	Required when `target` is `audit`. The 64-character lowercase hex Audit-ID of the record to retrieve.
agent_id	CONDITIONAL	Required when `target` is `chain_head` or `lifecycle`. The canonical Agent-ID whose chain head or lifecycle stream is being retrieved.
limit	MAY	When `target` is `lifecycle`, the maximum number of entries to return. Servers MAY cap the value.

Response shape depends on target:

target=audit: returns the JWS Compact serialization of the Attribution-Record identified by audit_id, along with the parsed payload for convenience. The relying party MUST recompute sha256(jws) and confirm it equals the requested audit_id before trusting the parsed payload.
target=chain_head: returns the most recently emitted Audit-ID for the named agent_id. Useful for chain walkers that need a starting point without an explicit Audit-ID.
target=lifecycle: returns recent lifecycle log entries for the named agent_id, ordered newest-first. Each entry carries an explicit format field with value "jws" or "cose" reflecting the envelope used to sign the lifecycle event (see ). The signed bytes are preserved on the wire so relying parties can re-verify signatures end-to-end. Servers MAY emit mixed-format streams when the operator has flipped the configured signing envelope between events; the per-entry format field disambiguates each line. The configured envelope is selected by operator policy (typically a mode setting in the audit configuration), with jws as the default and cose selected for SCITT-aligned deployments.
target=contract: returns the full record for a synthesized contract identified by synthesis_id. The response includes the resolved (method, path) pair, the recipe lineage (recipe name and captured recipe version), the originating Agent-ID, the contract hash, the negotiation origin, the issuance and expiration timestamps, and the contract's current lifecycle state. See for the contract concept and the RCNS substrate that produces and manages contracts.
target=rcns-attempt: returns diagnostic information for a failed RCNS synthesis attempt identified by an attempt identifier. Every 464 RCNS No Contract response from an RCNS-capable server MUST carry the RCNS-Attempt-Id response header naming an attempt record retrievable through this target. The attempt record contains the requested (method, path), the requesting Agent-ID, the resolved trust tier, the four-lock-gate evaluation outcomes, and any structured reason produced by the synthesis machinery. Attempt records are diagnostic surfaces only; servers MAY retain them in a ring buffer with a finite size and MAY evict older records when the buffer fills.

Servers MUST return 404 Not Found when the requested record or chain head is absent from the store. Servers MAY apply read-access control over INSPECT responses. Three access modes are defined:

public: any caller may read any stored audit record, chain head, or lifecycle entry. This is the default and matches the posture expected for chain walkers and external verifiers.
agent_only: a caller authenticated as Agent-ID X (via mTLS per , with the dispatcher's existing Agent-ID header cross-check against the verified certificate) may read records, chain heads, and lifecycle entries whose subject Agent-ID is X. Cross-agent reads are refused.
operator_only: only callers presenting an mTLS certificate whose public-key fingerprint matches an operator-controlled allowlist may read INSPECT responses.

When access control is configured and the request fails the configured check, servers MUST respond with 401 Unauthorized if the request presented no authenticated identity, and 403 Forbidden if the request presented an identity other than one permitted under the configured mode. The response body SHOULD identify which mode is in effect; it MUST NOT disclose operator-allowlist contents or other principals' Agent-IDs. INSPECT is intended for chain walkers, auditors, and external verifiers; it is no substitute for the Attribution-Record emitted on every response. The Attribution-Record carries the authoritative attestation of the current response; INSPECT retrieves a stored attestation by identifier after the fact. Idempotent: Yes. Primary error codes: 400, 401, 403, 404, 422.

SUMMARIZE Purpose: Request a concise synthesis of provided content or a referenced resource. The agent is requesting a cognitive operation on data, as distinct from retrieval of the data. Cognitive. SUMMARIZE Parameters

Parameter	Required	Description
source	MUST	Content inline (up to implementation limit) or URI reference
length	SHOULD	Target summary length: brief, standard, detailed
focus	MAY	Aspect to emphasize in the summary
format	MAY	Output format: bullets, prose, structured
audience	MAY	Intended reader context, for calibrating complexity

Response: Summary content with a source_hash and a confidence score. Idempotent: Yes.

PLAN Purpose: Produce a sequence of actions or method invocations that would accomplish a stated goal, without executing them. The response is a structured plan that the requesting agent (or its principal) reviews before committing to execution. Distinguished from the deprecated v06 SCHEDULE method (which committed the plan): PLAN is purely cognitive and produces no external state change. Cognitive. PLAN Parameters

Parameter	Required	Description
goal	MUST	Natural language or structured description of the desired outcome
constraints	SHOULD	Time, cost, scope, or policy constraints the plan must respect
available_methods	MAY	Methods the planning agent may assume the executor will support
context	MAY	Session context informing plan selection

Response: Plan document containing ordered_steps (each an AGTP method invocation specification), estimated_cost, confidence, and assumptions. Idempotent: Yes. Primary error codes: 422, 503.

PROPOSE Purpose: Submit a dynamic endpoint or method proposal to a server that has yet to declare support for the proposed method. PROPOSE initiates the runtime contract negotiation flow specified in and summarized in . The proposing agent submits a method name, parameter signature, and intended outcome; the server responds with acceptance, counter-proposal, or rejection. Cognitive. PROPOSE Parameters

Parameter	Required	Description
proposed_method	MUST	Uppercase ASCII method name being proposed
signature	MUST	Parameter set, response shape, and outcome semantics
intent	MUST	Natural language statement of what the method would accomplish
contract_version	SHOULD	Reference to the AGTP-METHODS contract version (default `AGTP-API/1.0`)
context	MAY	Session context informing the proposal

Response: Synthesis result. On accept, 263 Proposal Approved with the AGTP-METHODS endpoint definition, synthesis_id, and expires_at. On refuse, 463 Proposal Rejected with a structured reason. On async evaluation, 261 Negotiation In Progress with a proposal_id the agent can poll via QUERY /proposals/{proposal_id} (see ). Idempotent: No. Primary error codes: 261, 262, 263, 400, 459, 460, 463.

EXECUTE Purpose: Invoke a specific action with parameters, or dispatch a carried application-layer payload. EXECUTE is the protocol's generic mechanics carrier. When a higher-level agent framework is composed over AGTP, EXECUTE is the method that carries the framework's payload and dispatches it to the application based on the carried Content-Type. The Authority-Scope header is enforced against the action being performed; scope violations return 455. Mechanics. EXECUTE Parameters

Parameter	Required	Description
action	MUST	Identifier of the action to invoke (application-defined when carrying a higher-level protocol)
parameters	SHOULD	Action-specific parameters (structured)
payload	MAY	Application-layer payload, when EXECUTE is carrying a higher-level protocol invocation
payload_type	MAY	Content-Type of the carried payload, for dispatch
idempotency_key	MAY	Client-provided key enabling safe retry
context	MAY	Session context

Response: Execution result, with structure determined by the action or carried payload. Servers MUST return the AGTP envelope (status, task_id, attribution) wrapping the action's response. Idempotent: depends on the action; clients SHOULD supply idempotency_key for retry safety. Primary error codes: 403, 422, 455, 456, 503.

DELEGATE Purpose: Transfer execution of a task or method to a sub-agent or downstream system. Initiates a new AGTP session on behalf of the delegating agent, carrying forward authority lineage. Mechanics. DELEGATE Parameters

Parameter	Required	Description
target_agent_id	MUST	Identifier of the agent to delegate to
task	MUST	AGTP method call (or sequence) to execute
authority_scope	MUST	Scope granted to sub-agent MUST be a strict subset of delegating agent's scope
delegation_token	MUST	Signed token proving delegation authority
callback	SHOULD	AGTP endpoint for result delivery
deadline	MAY	Maximum time for task completion

Security note: the authority_scope in a DELEGATE request MUST NOT exceed the delegating agent's own Authority-Scope. Servers MUST enforce this and MUST return 455 Scope Violation with reason scope-exceeds-parent if violated. This is the protocol-level defense against authority laundering. Idempotent: No.

ESCALATE Purpose: Route a task, decision, or exception to a human principal or higher-authority agent when the current agent cannot or ought to stop. ESCALATE is the protocol-level expression of meaningful friction in AI systems as a first-class method. Mechanics. ESCALATE Parameters

Parameter	Required	Description
task_id	MUST	The task or method invocation triggering escalation
reason	MUST	Structured reason: confidence_threshold, scope_limit, ethical_flag, ambiguous_instruction, resource_unavailable
context	MUST	Full context needed for the escalation recipient to act
priority	SHOULD	urgent, normal, or low
recipient	MAY	Specific human or agent to escalate to; if absent, routes to default handler
deadline	MAY	Time by which a response is needed

Response: Escalation receipt with escalation_id and routing confirmation. The escalated task is paused until resolved via CONFIRM. Idempotent: Yes. An agent that escalates appropriately is functioning correctly. Governance frameworks built on AGTP can use escalation frequency and reason codes as observability signals for systemic issues.

CONFIRM Purpose: Explicit acknowledgment of a prior action, state, or data item. Creates a signed attestation record. Mechanics. CONFIRM Parameters

Parameter	Required	Description
target_id	MUST	ID of the action, booking, schedule, or item being confirmed
status	MUST	accepted, rejected, or deferred
reason	SHOULD (if rejected/deferred)	Explanation of the decision
attestation	MAY	Agent-signed confirmation payload for audit

Response: Confirmation receipt with timestamp and attestation_id. Idempotent: Yes.

SUSPEND Purpose: Pause a specific active session workflow in a recoverable state. Issues a resumption nonce the requesting agent uses to resume the session. Method-level SUSPEND is session-scoped and leaves registry lifecycle state or Agent Genesis validity. The distinction between method-level SUSPEND and lifecycle SUSPEND () is architectural: method-level SUSPEND is a workflow primitive; lifecycle SUSPEND is an administrative action on the agent's registry record. Mechanics. SUSPEND Parameters

Parameter	Required	Description
session_id	MUST	The session to suspend.
reason	SHOULD	Structured reason: `awaiting_input`, `resource_limit`, `scheduled_pause`, `external_dependency`.
resume_by	MAY	ISO 8601 deadline for resumption. If exceeded without RESUME, session transitions to expired.
checkpoint	MAY	Agent-provided state snapshot for resumption context. Stored by server for duration of suspension.

Response: Suspension receipt with the following structure: The resumption_nonce MUST be a cryptographically random 128-bit value encoded as base64url. It is single-use: once presented to resume a session, the nonce is invalidated and MUST NOT be accepted again. Idempotent: No. Primary error codes: 404, 408. Servers MUST generate nonces with at least 128 bits of entropy using a CSPRNG.

SUSPEND synthesis_id= SUSPEND accepts an alternative parameter set for releasing a synthesized contract the requesting agent originated. When invoked with synthesis_id instead of session_id, the call releases the named contract from the synthesis runtime, evicts it from active resolution, and emits an rcns_release event in the originating agent's lifecycle stream. SUSPEND synthesis_id Parameters

Parameter	Required	Description
synthesis_id	MUST	Opaque identifier of the contract being released, as issued by RCNS.
reason	SHOULD	Human-readable rationale recorded in the lifecycle event payload.

The release path is reserved for the originating agent (self-release): a caller presenting a synthesis_id MUST be the contract's originating_agent_id or the server MUST return 403 Forbidden. Operator-initiated contract eviction uses REVOKE target=contract () and produces an rcns_revoke event instead. The release leaves the originating agent's lifecycle state. See for the RCNS contract concept.

NOTIFY Purpose: Asynchronous push of information from an agent to a recipient. Expects no response. Fire-and-forget. Delivery confirmation (if required) returned via a subsequent CONFIRM from the recipient. Mechanics. NOTIFY Parameters

Parameter	Required	Description
recipient	MUST	Target Agent-ID, human endpoint, or broadcast group
content	MUST	Notification payload
urgency	SHOULD	critical, informational, or background
delivery_guarantee	MAY	at_most_once, at_least_once, or exactly_once
expiry	MAY	Timestamp after which delivery of the notification SHOULD cease

Response: Delivery receipt with notification_id. Idempotent: No.

ACTIVATE Purpose: Transition an agent into the Active registry lifecycle state. The responding server records the transition, signs a lifecycle event into the agent's per-agent lifecycle stream, and makes the agent eligible to be addressed by AGTP requests. The canonical Agent-ID MUST already exist (its Agent Genesis MUST have been issued and loaded); ACTIVATE never mints Agent-IDs. Lifecycle. A successful ACTIVATE is the publish event for the agent: it is the trigger for the governance platform's registration of the agent with the Agent Name Service of its zone per , and for the agent's first ANNOUNCE into the presence substrate per . Neither is a separate registration step an operator performs; both follow from the lifecycle transition, so that an agent is findable exactly when it is Active and never otherwise. DEACTIVATE, REVOKE, and DEPRECATE are the corresponding withdrawal events. ACTIVATE Parameters

Parameter	Required	Description
agent_id	MUST	Canonical Agent-ID of the agent being activated.
reason	MAY	Human-readable rationale recorded in the lifecycle event payload.
actor	SHOULD	Identifier of the operator or registrar invoking the transition. Recorded in the lifecycle event.

Response: A status document containing the new status (active), the previous_status, the event_type (agent-genesis-issued or agent-lifecycle-reinstated depending on whether the agent has prior lifecycle history), and the audit_id of the signed lifecycle event. When the agent is already in the Active state, the server MUST return 200 OK with a noop: true flag and MUST NOT emit a duplicate lifecycle event. Lifecycle events are signed with the responding server's manifest signing key. The signed envelope is appended to the per-agent lifecycle stream and is retrievable via INSPECT target=lifecycle per . Two envelope formats are defined: JWS Compact per and COSE_Sign1 per . Servers select one envelope by operator policy; both are normatively conformant and the choice leaves the wire contract of the Lifecycle method itself, only the on-disk and INSPECT-returned event representation. Servers that have yet to provision a manifest signing key MUST emit lifecycle events with alg: none per the fallback in ; relying parties MUST treat such events as unverified. See for the envelope format details and the Audit-ID derivation rule for each envelope. ACTIVATE is the protocol-level replacement for the package-binding ACTIVATE method extension referenced in earlier revisions of this document. The two transactions converge: a governance platform that operates a .nomo package binding flow issues an ACTIVATE on completion of the binding to record the state transition on the wire. Idempotent: No. Authorization: see . Primary error codes: 400, 401, 403, 404, 422.

DEACTIVATE Purpose: Transition an agent out of the Active registry lifecycle state, typically into Suspended. The responding server records the transition, signs a lifecycle event, and ceases to treat the agent as eligible to receive AGTP requests until a subsequent REINSTATE returns it to Active. DEACTIVATE is reversible via REINSTATE; permanent retirement uses REVOKE; controlled end-of-life uses DEPRECATE. Lifecycle. DEACTIVATE Parameters

Parameter	Required	Description
agent_id	MUST	Canonical Agent-ID of the agent being deactivated.
reason	SHOULD	Human-readable rationale recorded in the lifecycle event payload (e.g., `compliance-hold`, `fraud-review`, `operator-pause`).
actor	SHOULD	Identifier of the operator or registrar invoking the transition.

Response: A status document containing the new status (suspended), the previous_status, the event_type (agent-lifecycle-suspended), and the audit_id of the signed lifecycle event. When the agent is already in a non-Active state, the server MUST return 200 OK with noop: true and MUST NOT emit a duplicate lifecycle event. Idempotent: No. Authorization: see . Primary error codes: 400, 401, 403, 404, 422.

REVOKE Purpose: Permanently retire an agent's canonical Agent-ID. The responding server records the transition, signs a lifecycle event, and refuses all subsequent requests addressed to the agent. The Agent-ID MUST NOT be reissued to another agent. REVOKE is non-reversible; an agent that needs to return to service after REVOKE requires a new Agent Genesis and a new canonical Agent-ID. Lifecycle. REVOKE Parameters

Parameter	Required	Description
agent_id	MUST	Canonical Agent-ID of the agent being revoked.
reason	MUST	Human-readable rationale recorded in the lifecycle event payload (e.g., `compromise-detected`, `principal-request`, `policy-violation`).
actor	SHOULD	Identifier of the operator or registrar invoking the transition.

Response: A status document containing the new status (retired), the previous_status, the event_type (agent-genesis-revoked), and the audit_id of the signed lifecycle event. When the agent is already in the Retired state, the server MUST return 200 OK with noop: true and MUST NOT emit a duplicate lifecycle event. Servers SHOULD propagate REVOKE events to subscribing registries and Agent Name Service operators within 60 seconds per . A revoked agent's certificate remains valid for TLS-layer authentication only insofar as the revocation event has yet to propagate; relying parties that require strict revocation enforcement MUST consult the lifecycle stream for the Agent-ID before treating an AGTP exchange with that agent as authoritative. Idempotent: No. Authorization: see . Primary error codes: 400, 401, 403, 404, 422.

REVOKE target=contract REVOKE accepts an alternative parameter set for revoking a synthesized contract identified by synthesis_id, leaving the agent itself in place. When invoked in this form, REVOKE evicts the contract from the synthesis runtime, refuses subsequent presentations of the synthesis_id with 464 contract-revoked, and emits an rcns_revoke event in the originating agent's lifecycle stream. REVOKE target=contract Parameters

Parameter	Required	Description
target	MUST	The literal string `contract`.
synthesis_id	MUST	Opaque identifier of the synthesized contract being revoked, as issued by RCNS.
reason	SHOULD	Human-readable rationale recorded in the lifecycle event payload.
actor	SHOULD	Identifier of the operator or originating agent invoking the revocation.

Authorization for REVOKE target=contract is independent of the lifecycle-method authorization in ; servers MUST accept the invocation from either the originating agent (self-revocation) or from operators carrying the inspect:all scope. Cross-agent revocation by any other principal MUST return 403 Forbidden. The contract revocation leaves transition the originating agent's lifecycle state. See for the RCNS contract concept and the negotiation_origin field that drives revocation semantics.

REVOKE target=stale-contracts REVOKE accepts a third parameter set for sweeping synthesized contracts whose captured recipe_version diverges from the current loaded recipe version. The sweep is an operator surface for handling drift after a recipe edit; the full normative semantics (sweep walk, per-contract disposition, grandfather vs invalidate modes, the emitted rcns_release events for evictions) are specified in the Stale Contract Sweep section in . REVOKE target=stale-contracts Parameters

Parameter	Required	Description
target	MUST	The literal string `stale-contracts`.
mode	MAY	One of `grandfather` or `invalidate`. Default is the server's `on_policy_change` configuration value. Invalid values return `400 Bad Request`.
actor	SHOULD	Identifier of the operator invoking the sweep, recorded on emitted `rcns_release` events.

Authorization requires the operator inspect:all scope token. The sweep leaves every agent's lifecycle state; evicted contracts produce rcns_release events on their originating agents' lifecycle streams per the Stale Contract Sweep section in .

REINSTATE Purpose: Transition a Suspended agent back to the Active registry lifecycle state. The responding server records the transition, signs a lifecycle event, and resumes treating the agent as eligible to receive AGTP requests. REINSTATE is the recovery counterpart to DEACTIVATE; an agent that was DEACTIVATEd for a recoverable reason (compliance hold lifted, fraud review cleared, operator pause ended) returns to service via REINSTATE. REINSTATE preserves the canonical Agent-ID and the underlying Agent Genesis; the reinstated agent is the same agent it was before suspension. Lifecycle. REINSTATE Parameters

Parameter	Required	Description
agent_id	MUST	Canonical Agent-ID of the agent being reinstated.
reason	SHOULD	Human-readable rationale recorded in the lifecycle event payload (e.g., `compliance-hold-lifted`, `fraud-review-cleared`, `operator-resume`).
actor	SHOULD	Identifier of the operator or registrar invoking the transition.

Response: A status document containing the new status (active), the previous_status, the event_type (agent-lifecycle-reinstated), and the audit_id of the signed lifecycle event. When the agent is already in the Active state, the server MUST return 200 OK with noop: true and MUST NOT emit a duplicate lifecycle event. When the agent is in the Retired state, the server MUST return 422 Unprocessable Entity; REVOKE is non-reversible and REINSTATE cannot bring a Retired agent back to service. Idempotent: No. Authorization: see . Primary error codes: 400, 401, 403, 404, 422.

DEPRECATE Purpose: Transition an agent to the Deprecated registry lifecycle state. A Deprecated agent continues to accept AGTP traffic (distinguishing DEPRECATE from REVOKE and DEACTIVATE), but the deprecation event signals planned end-of-life. Clients addressing the agent SHOULD migrate to a successor agent or capability within the migration window declared in the event payload. DEPRECATE is the controlled-retirement path: it gives consumers time to migrate before traffic stops. Lifecycle. DEPRECATE Parameters

Parameter	Required	Description
agent_id	MUST	Canonical Agent-ID of the agent being deprecated.
reason	SHOULD	Human-readable rationale recorded in the lifecycle event payload.
successor_agent_id	MAY	Canonical Agent-ID of a successor agent that clients SHOULD migrate to.
migration_deadline	MAY	RFC 3339 timestamp after which the agent MAY be transitioned to Retired without further notice.
actor	SHOULD	Identifier of the operator or registrar invoking the transition.

Response: A status document containing the new status (deprecated), the previous_status, the event_type (agent-lifecycle-deprecated), and the audit_id of the signed lifecycle event. When the agent is already in the Deprecated state, the server MUST return 200 OK with noop: true and MUST NOT emit a duplicate lifecycle event. A Deprecated agent MUST continue to serve requests under the same Authority-Scope and trust posture it held before deprecation. Servers SHOULD surface the deprecation signal to clients on every response from the deprecated agent; the specific surfacing mechanism (response header, response body field, DISCOVER listing flag) is implementation-defined and MAY be specified normatively in a future revision. A subsequent REVOKE against a Deprecated agent transitions it to the Retired state and stops traffic. A subsequent ACTIVATE or REINSTATE against a Deprecated agent transitions it back to Active (cancelling the deprecation); the cancellation MUST be recorded as a separate lifecycle event. Idempotent: No. Authorization: see . Primary error codes: 400, 401, 403, 404, 422.

Lifecycle Method Authorization Lifecycle methods (ACTIVATE, DEACTIVATE, REINSTATE, REVOKE, DEPRECATE) transition the registry state of an agent's canonical Agent-ID. Because the registry state determines whether AGTP infrastructure treats the agent as operational, unrestricted invocation of these methods would allow any caller to suspend, retire, or deprecate any agent. Servers MUST implement an authorization model for lifecycle methods. Two modes are defined; future revisions MAY define additional modes.

open:: Any caller may invoke any lifecycle method against any agent the server hosts. This mode is appropriate only for development and single-tenant deployments where the operator implicitly trusts all callers. It is the simplest default and MAY be the implementation default; it MUST NOT be used in multi-tenant or production deployments.
genesis_issuer:: A lifecycle method invocation MUST be presented over mTLS per , and the verified client certificate's public-key fingerprint MUST equal the Genesis-issuer fingerprint recorded for the target Agent-ID. The Genesis-issuer fingerprint is computed as sha256(raw_ed25519_public_key_bytes(Agent_Genesis.issuer_public_key)), giving a 256-bit value rendered as 64 lowercase hexadecimal characters. Only the registrar that issued an agent's Agent Genesis may transition that agent's lifecycle. Agents whose Agent Genesis is unloaded by the server (transport-only deployments) have no Genesis-issuer fingerprint to compare against; lifecycle methods against such agents under this mode MUST be refused.

When authorization fails, servers MUST respond with 401 Unauthorized if the request presented no verified client certificate, and 403 Forbidden if the request presented a certificate whose fingerprint differed from the Genesis-issuer requirement. The response body SHOULD identify which mode is in effect. Lifecycle method authorization is independent of INSPECT read-access control. An operator MAY configure lifecycle_auth = genesis_issuer (write-side governance) alongside read_acl = public (read-side transparency) to support a regulator-friendly posture in which the agent's lifecycle history is publicly auditable but only the issuing registrar may transition its state. Implementations MUST log lifecycle authorization failures.

Method Summary Table AGTP Core Method Summary

Method	Group	Intent	State-Modifying	Idempotent	Primary Error Codes
QUERY	Cognitive	Retrieve information	No	Yes	404, 422
DISCOVER	Cognitive	Locate agents or resources	No	Yes	422
DESCRIBE	Cognitive	Retrieve endpoint capabilities	No	Yes	404, 422
INSPECT	Cognitive	Retrieve stored audit, chain head, or lifecycle records	No	Yes	400, 401, 403, 404, 422
SUMMARIZE	Cognitive	Synthesize content	No	Yes	400, 422
PLAN	Cognitive	Produce an unexecuted plan	No	Yes	422, 503
PROPOSE	Cognitive	Submit a dynamic endpoint proposal	No	No	261, 262, 263, 400, 459, 460, 463
EXECUTE	Mechanics	Invoke an action or carried payload	Yes	Per action	262, 403, 422, 455, 456, 503
DELEGATE	Mechanics	Transfer task to sub-agent	Yes	No	262, 403, 551
ESCALATE	Mechanics	Defer to human or authority	Yes	Yes	404
CONFIRM	Mechanics	Attest to a prior action	Yes	Yes	404, 400
SUSPEND	Mechanics	Pause session workflow	Yes	No	404, 408
NOTIFY	Mechanics	Push information	No	No	400, 404
ACTIVATE	Lifecycle	Transition agent to Active	Yes	No	400, 401, 403, 404, 422
DEACTIVATE	Lifecycle	Transition agent out of Active	Yes	No	400, 401, 403, 404, 422
REINSTATE	Lifecycle	Return Suspended agent to Active	Yes	No	400, 401, 403, 404, 422
REVOKE	Lifecycle	Permanently retire Agent-ID	Yes	No	400, 401, 403, 404, 422
DEPRECATE	Lifecycle	Signal planned end-of-life; agent continues serving	Yes	No	400, 401, 403, 404, 422

Method Registry and Extensibility AGTP defines a formal Method Registry maintained by IANA (see ). Any party may submit a new method for registration. The registration procedure is Expert Review, and registration MUST be accompanied by a published specification, at minimum an IETF Internet-Draft or equivalent publicly available document. Registered methods MUST:

Have a unique uppercase ASCII name
Define required and optional parameters
Define expected response structure
Specify idempotency behavior
Specify applicable error codes
Include a security considerations section
Be accompanied by a published reference specification (Internet-Draft or RFC)
Appear in the AGTP-METHODS approved method catalog . The verb list is the authoritative source for what method names are recognized by AGTP servers; registered methods are a subset of the method catalog with formal IETF registration. Submissions whose method name is absent from the AGTP-METHODS method catalog MUST be rejected by the Designated Expert.

Experimental methods MAY be used prior to registration using the X- prefix convention (e.g., X-NEGOTIATE). Experimental methods MUST NOT be used in production deployments without registration. Experimental methods are subject to verb-list validation; non-conformant experimental methods MUST be rejected with 459 Method Violation by AGTP-aware infrastructure components.

Verb-List Validation AGTP servers MUST validate inbound method names against the AGTP-METHODS approved method catalog. A method name absent from the method catalog MUST result in a 459 Method Violation response. A method name in the method catalog whose path violates AGTP-METHODS path grammar MUST result in a 460 Endpoint Violation response. A method name and path that are individually valid, with no endpoint exposed at the combination by the server's policy, MUST result in a 405 Method Not Allowed response, with the response body listing allowed methods for the path. The full contract validation model is specified in . Capability negotiation occurs during session establishment. The server returns a Supported-Methods header listing the methods it implements. Clients SHOULD check this list before invoking non-core methods. The Negotiation-ID header is used to correlate turns within a dynamic endpoint negotiation sequence (see ). It MUST be a UUID generated by the service upon receiving a PROPOSE request and MUST be echoed in all subsequent turns of the same negotiation. Maximum three turns before the agent MUST ESCALATE. QUOTE is defined as a Tier 2 Standard Extended Method in . QUOTE provides pre-flight cost estimation for a proposed method invocation: the requesting agent submits a proposed method call; the server returns a Cost-Estimate response without executing the method. Servers supporting budget negotiation via the Budget-Limit header SHOULD implement QUOTE to enable agents to validate cost before committing to execution. Servers that implement QUOTE MUST list it in the Supported-Methods response header at session establishment.

Dynamic Endpoint Negotiation (Summary) An agent that needs a method or endpoint the server has yet to declare submits a PROPOSE request carrying an endpoint definition in the form specified by . The server evaluates the proposal against the method catalog, path grammar, its own policy, and the four-lock dispatcher gate, and answers with 263 Proposal Approved (the endpoint is synthesized and the response names it), 261 Negotiation In Progress, 262 Authorization Required, or 463 Proposal Rejected with a structured reason. A server may also treat an unregistered method and path pair as a synthesis candidate without a PROPOSE, delivering a contract with 461 RCNS Contract Available or inline under a Contract-Synthesized header. The full negotiation protocol, including contract scoping, lifecycle, and revocation, is specified in .

Extended Method Vocabulary (Summary) Methods beyond the eighteen-method floor are registered in the catalog specified by : at catalog version 1.0.0, 425 methods in nine categories, with the floor as the embedded set and the five HTTP verbs mapped to their preferred AGTP forms as legacy entries. Industry profiles, custom methods declared in a server's method policy, and the method properties (safe, idempotent, action, authority-bearing) are specified there, with the empirical basis for intent-named methods documented in . A method name in neither the floor nor the catalog nor the server's custom set is refused with 459 Method Violation; a path that leaks a method name is refused with 460 Endpoint Violation.

Delegated Authority AGTP specifies delegation on two sides of execution. The pre-authorization side, specified here, is the conveyance of narrowed authority from a delegating agent to a sub-agent before the sub-agent's request is accepted. The post-execution side, specified in , is the attribution of a completed action to the sequence of agents that caused it, through the prior_actions chain in the Attribution-Record. The Delegation Sequence a request carries is the same sequence its Attribution-Record later records, so the two sides compose.

The Delegation Sequence A Delegation Sequence is the ordered set of DELEGATE invocations that produced a request. Each hop is minted by one DELEGATE invocation () and consists of:

the delegating agent's canonical Agent-ID (the parent),
the sub-agent's canonical Agent-ID (the delegate),
the authority_scope granted to the delegate, which MUST be a strict subset of the parent's effective Authority-Scope at the time of minting, and
the delegation_token: the parent's signature over the three fields above, the parent's own hop (or the token origin for the first hop), the minting time, and an expiry.

The strict-subset rule is enforced at mint: a server processing a DELEGATE whose authority_scope falls outside a strict subset of the delegating agent's effective scope MUST refuse with 455 Scope Violation and reason scope-exceeds-parent (). Same-scope relay, where a delegate exercises exactly its parent's scope, is therefore outside delegation; it is a request the parent makes itself, with the relay as transport. The rule is also enforced at verify (), so a sequence minted by a non-conformant server fails at the first conformant verifier.

The Delegation-Chain Header A request made under delegated authority MUST carry the Delegation-Chain header. A request the agent makes under its own authority MUST NOT carry it. The header carries the Delegation Sequence as an ordered list of hops, origination to current: The first hop names the originating agent and carries its token signed over origin. Each subsequent hop names the delegate of the previous hop. The last hop names the agent making the request, whose Agent-ID MUST equal the request's Agent-ID header.

Delegation Token Format A delegation token is the compact JWS serialization of , algorithm EdDSA, kid equal to the parent's Agent-ID, over the canonical form of: ", "delegate": "", "scope": [ "", ... ], "parent_tok":"", "iat": , "exp": , "depth": <0 for the origin hop, parent depth plus 1 after>, "authority": "" } ]]> The signing key is the parent's agent_public_key as published in its Identity Document () or bound by . For the origin hop the originating agent signs over parent: "origin" and parent_tok: null; its scope MUST be a subset of its own Identity Document grant, which is the check performs at step 3 for that hop. parent_tok binds each hop to the exact parent token, so a parent swap changes the digest and fails step 2 even when the swapped-in parent is a valid agent. authority is the optional digest reference described in . The header is a carrier. The claim it carries, that the requesting agent holds authority narrowed from the origin through every listed hop, exists only after verification.

Verification A server receiving a request with a Delegation-Chain header MUST verify the sequence before dispatch, in order from the first hop to the last. Verification is a function of a fixed input set: the header as received, the request's Agent-ID and Authority-Scope, the verification time, the server's configured maximum depth, and the Identity Documents and lifecycle states resolved for the listed Agent-IDs. A verifier MUST NOT consult any other input and MUST NOT apply local policy inside verification; the relying party applies its policy to the result afterwards, so that two conforming verifiers given the same inputs produce the same result. For every hop the verifier MUST check:

Membership. The hop's Agent-ID resolves () to an agent in the Active lifecycle state. Failure reason: member-inactive.
Parent re-verification. The hop's delegation token verifies under the parent's published key, and the parent named in the token equals the previous hop's Agent-ID (or origin for the first hop). A token that verifies under a key other than the listed parent's, or that names a different parent, is a parent swap. Failure reason: link-unverifiable.
Attenuation. The hop's granted scope is a strict subset of the parent's scope as carried in the parent's hop (for the first hop, of the originating agent's identity-document scope). Failure reason: scope-exceeds-parent.
Freshness. The hop's token is unexpired, and the minting time is no earlier than the parent hop's minting time. Failure reason: chain-expired.
Depth and cycles. The sequence length is within the server's configured maximum depth (default 8), and no Agent-ID appears twice. Failure reasons: depth-exceeded, cycle-detected.

Verification has three outcomes. It is valid when every check passes; invalid when any check fails on an input the verifier holds; and indeterminate when a check cannot run because an input is unavailable (an Agent-ID that cannot be resolved, a lifecycle state the registry failed to answer for, an Identity Document that failed to fetch). An indeterminate outcome is never reported as valid and never reported as invalid; it is carried as 551 with evaluation: incomplete and missing_input naming the input (), and the relying party MUST deny by default. A verifier that is offline for the registry therefore produces indeterminate for every delegated request; the alternatives, admitting on stale state or refusing as if the chain were broken. The accepted result of a valid verification is the effective scope: the scope of the last hop, which by construction is the intersection of every hop's scope with the origin's. The request's claimed Authority-Scope, when present, MUST be a subset of the effective scope; the endpoint's required_scopes are evaluated against the claimed or effective scope exactly as for an undelegated request (). Verification MUST be repeated on every request; a verified sequence MUST NOT be cached as authority across requests, since membership and freshness change.

Failure Behavior A verification failure MUST be refused with 551 Authority Chain Broken, with evaluation: refused for an invalid outcome or evaluation: incomplete for an indeterminate one, the reason token from the list above (or input-unavailable with missing_input when indeterminate), and, in failing_hop, the zero-based index of the hop that failed. The server MUST NOT dispatch any part of the request, MUST log the event, and MUST produce an Attribution-Record for the refusal as for any failure (). A request whose Agent-ID differs from the last hop's Agent-ID is refused with 551 and reason link-unverifiable. A Delegation-Chain header on a request whose method is a lifecycle method () is refused with 551 and reason scope-exceeds-parent, since lifecycle authority is never delegable.

Evidence of the Delegator's Authority A verified Delegation Sequence proves that no hop exceeds its parent and that the origin hop is within the originating agent's Identity Document grant. It proves that the registrar that issued the agent recorded that grant; it leaves unproven that the person or organization behind the registrar could lawfully confer it. For most traffic the registrar's record is sufficient. Where a relying party in another administrative domain needs the stronger statement (a bank receiving a payment instruction from a broker's agent needs to know that the broker's signatory could delegate payments at all), AGTP carries the evidence; producing it is the authority source's job. The origin hop's authority field MAY carry a digest reference to an authority assertion: a signed statement from an authority source, separate from the sequence, of the powers the delegator could delegate. AGTP defines no authority assertion format of its own. Two are recognized: the vLEI Role Credential chain (OOR, ECR, AUTH) carried per , whose AUTH credential names the human signatory and the role under which the agent was authorized; and the Authority Assertion of the WIMSE agent mandate work, when the relying party's trust framework accepts it. A verifier that is asked by policy to require authority evidence MUST check that the assertion's delegator matches the origin hop's Owner-ID and that the origin hop's scope is within the assertion's stated powers; an origin hop with no authority reference under such a policy is indeterminate with missing_input: authority. Typed constraints on delegated authority (bounded amounts, time windows, accumulated budgets, co-signature thresholds) are the natural next step for payment-grade delegation. AGTP's Authority-Scope is a token set and Budget-Limit is its only numeric constraint; a constraint vocabulary over scope tokens is planned.

What Each Artifact Asserts Each artifact in a delegated request asserts one thing, and a verifier MUST NOT treat a claim as established by an artifact whose role fails to cover it. Delegation Artifacts and Their Claims

Artifact	Asserts	Outside its claim
Agent Genesis	that a registrar issued this Agent-ID to this owner with this grant	that the owner could lawfully confer the grant
Agent Identity Document	the agent's current grant, key, and lifecycle state, as its issuer records them	that the sender of any request is this agent
`Request-Signature`	that the sender of this request holds the agent's current key	anything about delegated authority
origin hop token	that the originating agent narrowed its own grant to this scope	that the grant itself was within the owner's authority
subsequent hop token	that the named parent conferred this scope on this delegate, and that it was within the parent's hop	that the delegate was unmanipulated in requesting
authority assertion (when carried)	the powers the delegator could delegate, per the authority source	that any delegation was in fact made
Attribution-Record	what the agent did, after the fact	that the action was authorized before it ran

A valid sequence shows that the request is within delegated authority. It leaves unshown whether the requesting agent was manipulated into making it; that is outside what any artifact in the sequence can assert, and a relying party that needs it looks to the governance platform's runtime verdict () and to the Governance Token's action digest; the chain has nothing to say about it.

Mapping to the WIMSE Chain Convention The multi-hop convention converging across the WIMSE agent identity work carries three claims: sub is the principal at every hop, client_id is the current actor, and act is the history of prior actors. AGTP carries the same three facts in its own elements, and a Delegation Sequence maps onto the convention without loss: Delegation Sequence Mapped to the WIMSE Chain Convention

WIMSE claim	AGTP element
`sub` (principal at every hop)	Owner-ID of the originating agent, resolved from its Identity Document and unchanged along the sequence
`client_id` (current actor)	`Agent-ID` of the request, equal to the last hop
`act` (prior actors)	the hops of `Delegation-Chain` before the last, in order
scope at this hop	effective scope of
root authority evidence	the origin hop checked against the originating agent's Identity Document grant, plus the optional authority assertion reference of for the delegator's own powers

Narrowing follows the subset rule stated in that work: what a hop passes on is a strict subset of what it received, token by token over the Authority-Scope grammar, the narrowing party signs the hop, and a party that forwards without narrowing makes no authorization claim and appears in no hop. AGTP states its staleness bound as S plus L. S is the maximum age of the authorization state a verifier relied on when it admitted a request: the Identity Document freshness window of and the Request-Signature acceptance window (). L is the maximum lifetime of a hop's delegation token without re-validation, which is the token's expiry checked at step 4 of ; L MUST NOT exceed 24 hours and SHOULD be shorter for action methods. The bound limits new admissions; an admitted action runs to completion. Absence of enforcement is an unbounded S, the opposite of a small bound: a verifier that skips a check has an unbounded S for that check and MUST record the request as possession-unproven or sequence-unverified. Implementations SHOULD publish one test vector exactly on each limit.

Status of This Section Specified in this revision. The reference implementation targets verification steps 1 through 5 and the request signature in its v10 build; revocation of a member after minting is caught at step 1 on the next request, and the continuity of that check across certificate expiry and session boundaries is planned (). Delegation across organizations composes with draft-rampalli-pedigree, draft-rampalli-cross-org-delegation-mapping, and draft-hulea-wimse-agent-mandate: AGTP's per-hop attenuation and parent re-verification satisfy the chain requirements those documents state, the origin check and the authority assertion reference of correspond to the mandate work's Authority Assertion, the three-outcome verification and the validator-versus-policy split follow its Validation Result model, and an AGTP Delegation Sequence can be mapped row for row into the cross-organization template. AGTP carries whichever chain format the WIMSE group settles on and competes with none of them.

Composition with Higher-Level Frameworks AGTP is intended to compose with, never replace, MCP, A2A, ACP, ANP, and other agent application frameworks. AGTP is the substrate those frameworks need to operate at scale. The frameworks define what agents say to one another; AGTP defines how those messages move, who is allowed to send them, and how their effects are attributed. This section establishes composition with higher-level frameworks as a first-class use case of AGTP, specifies the precedence rules between AGTP transport semantics and framework-level messaging semantics, and provides the canonical mapping table from common framework concepts onto AGTP primitives. Detailed composition profiles for each framework are specified in .

Substrate Model In a composed deployment, AGTP supplies four properties at the wire level that no framework currently supplies natively:

Identity at the protocol level. Every AGTP request carries a canonical Agent-ID in the Agent-ID header. The framework's payload can omit identity; identity is established by the transfer protocol.
Authority bounded at the protocol level. The Authority-Scope header declares what the requesting agent is permitted to do. Servers enforce scope before dispatching to the framework's payload handler. A scope violation returns 455 at the AGTP layer, before the framework sees the payload.
Attribution at the protocol level. Every method invocation produces an Attribution-Record. The framework's payload can omit re-implement audit logging; the attribution is produced by the transfer protocol.
Delegation at the protocol level. Multi-hop agent workflows carry their Delegation Sequence in the Delegation-Chain header, verified per , independent of framework-level concepts of "session" or "task."

A framework composed over AGTP can shed the parts of its design that exist only because HTTP lacked these properties. The result is a framework that can focus on its actual contribution (tool semantics, conversational structure, multi-agent choreography) while the substrate handles the cross-cutting concerns.

EXECUTE as the Generic Carrier When a framework is composed over AGTP, EXECUTE is the canonical method that carries the framework's payload. The carried payload's Content-Type identifies the framework; the AGTP server dispatches the payload to the framework's handler. See . The EXECUTE invocation supplies:

The framework identifier (via payload_type).
The framework-specific operation (via the action parameter).
The framework-specific payload (via the payload parameter).
An optional idempotency_key enabling safe retry.

The AGTP envelope (status, task_id, attribution) wraps the framework's response. A framework that wishes to expose a particular operation as a first-class AGTP method (instead of carrying it through EXECUTE) MAY register a catalog method per ; this is reserved for frameworks whose operations are widely used enough to justify a dedicated verb.

Precedence Rule AGTP headers (Agent-ID, Authority-Scope, Delegation-Chain, Session-ID, Task-ID) MUST take precedence over equivalent fields in a carried framework payload for routing, enforcement, audit, and identity purposes. Infrastructure components including SEPs and governance gateways MUST use AGTP header values for all protocol-level decisions. Framework-level identity, session, or scope fields MAY be present in the body for application-layer use but MUST NOT override AGTP header values. If an inconsistency is detected between an AGTP header and a corresponding framework-level field, the AGTP header is authoritative; the inconsistency SHOULD be logged.

Composition Profiles The canonical mapping of A2A, MCP, and ACP concepts to AGTP constructs, the external identity provider patterns, the HTTP gateway profile, and the wire examples are specified in . Two positions this document holds for those profiles:

The A2A provenance chain maps to the Delegation Sequence () on the pre-authorization side and to the prior_actions chain of on the attribution side.
Tool and resource identity is carried through composition profiles; there is no first-class AGTP header for it. This is a deliberate choice under review; a first-class carrier is planned if working group review prefers it.

Merchant Identity and Agentic Commerce Binding

Overview AGTP specifies agent-side identity through the Agent Genesis, canonical Agent-ID, Agent Identity Document, and Trust Tier model. PURCHASE invocations carrying payments:purchase in the Authority-Scope header and a Budget-Limit constraint are fully governed on the sending side. The receiving side of a PURCHASE, the merchant counterparty, lacks an equivalent protocol-level identity in the base specification. The merchant-side identity model is specified in . The integration is hook-based: this document registers the required headers (), the 458 status code (), and the merchant and intent Authority-Scope domains; the detailed semantics, Merchant Manifest Document schema, Merchant Genesis structure, and counterparty verification procedure are specified in the companion.

Merchant Identity Headers (Summary) PURCHASE invocations in a fully conformant v04 deployment carry the following additional headers:

Merchant-ID: canonical identifier of the intended merchant counterparty.
Merchant-Manifest-Fingerprint: SHA-256 fingerprint of the Merchant Manifest Document the requesting agent verified during pre-flight counterparty verification.
Intent-Assertion: detached JWT carrying principal-authorized purchase intent, forwardable to payment networks as standalone evidence.
Cart-Digest: digest of a structured cart returned by a prior QUOTE invocation, binding this PURCHASE to that cart.

Full field definitions, wire examples, and security requirements are in .

Security Considerations This section satisfies the mandatory IETF Security Considerations requirement. All AGTP implementations MUST address the considerations described here.

Mandatory TLS All AGTP connections MUST use TLS 1.3 or higher. Implementations MUST reject connections using TLS 1.2 or below. Certificate validation follows standard PKI practices per . Servers MUST present a valid certificate.

Agent Identity Verification: Three Levels AGTP defines three distinct levels at which agent identity and Authority-Scope can be verified. Each level serves a different deployment profile and operational tradeoff. Understanding the distinction is essential for implementers: the AGTP Agent Certificate extension () is OPTIONAL, and base AGTP provides cryptographic verification at the application layer without it. Level 1 - Self-asserted headers (raw request fields). Every AGTP request MUST include the Agent-ID header, which references the agent identity document carrying the principal identifier and Authority-Scope. As a raw header value on an individual request, Agent-ID is self-asserted: a client writes the value into the request and the server records what was written. Level 1 verification is limited to mandatory logging and anomaly detection against the recorded stream. This is the minimum baseline every AGTP implementation provides. Level 2 - Application-layer cryptographic verification (signed Agent Identity Document plus proof of possession). A canonical Agent-ID resolves to a signed Agent Identity Document () that carries the Agent Genesis's Authority-Scope grant and the agent's current agent_public_key, signed by the issuer. A verifier (including a stranger with no prior relationship to the agent's organization) verifies identity, scope, and possession at the application layer by performing the following steps:

Resolve the canonical Agent-ID to retrieve the signed Agent Identity Document.
Verify the issuer's signature on the document against the issuer's published key.
Confirm that the canonical Agent-ID in the document matches the hash of the Agent Genesis.
Read the Authority-Scope grant and the agent_public_key from the verified document.
Verify the request's Request-Signature under that key per .

Steps 1 through 4 establish that the identity exists and what it may do. Step 5 establishes that the sender is that identity. A verifier that performs steps 1 through 4 and skips step 5 has verified a document and no sender, and the request is at Level 1 for every purpose that depends on who sent it. Level 2 is available in base AGTP without the Agent Certificate extension and is the identity mechanism the protocol depends on. Level 3 - TLS-layer cryptographic verification (AGTP-CERT extension). The AGTP Agent Certificate extension binds the canonical Agent-ID and Authority-Scope to an X.509 v3 certificate presented during TLS 1.3 mutual authentication. The principal identifier remains in the agent identity document referenced by Agent-ID. Level 3 accelerates the Level 2 check to the TLS handshake and enables Scope-Enforcement Points (SEPs) to verify Authority-Scope at O(1) per-request cost without application-layer access. Level 3 is an acceleration and enforcement path for Level 2, which it presupposes. Deployments that require line-rate scope enforcement at infrastructure layers (load balancers, governance gateways) SHOULD implement .

Note: The Agent Certificate extension and the Agent Genesis mechanism may be subject to pending intellectual property claims. See and the IPR Notice preceding the Abstract for details. The licensor is prepared to grant a royalty-free license to implementers.

Every AGTP server MUST log the Agent-ID value from every request and the principal identifier resolved from the corresponding agent identity document, creating an attributable audit trail at Level 1 even in deployments that omit Level 2 retrieval or Level 3 transport binding.

Authority Scope Enforcement The Authority-Scope header declares what actions the agent is authorized to take. Compliant AGTP servers MUST parse the Authority-Scope on every request, return 455 Scope Violation for any method that exceeds declared scope, and log all scope violations for audit purposes. At Level 1, scope declarations are self-asserted in the request header, analogous to scope assertions in OAuth 2.0 . At Level 2, scope is cryptographically verifiable through the signed Agent Identity Document; servers SHOULD retrieve and verify the manifest for any Agent-ID whose declared scope exceeds read-only operations. Level 3 cryptographically signed and infrastructure-enforced scopes are defined in .

Threat Model

Agent Spoofing Threat: A malicious actor forges the Agent-ID header to impersonate a trusted agent. Mitigation: Level 2 application-layer verification binds a declared Agent-ID to the signed Agent Identity Document retrieved via canonical ID resolution. A forged Agent-ID either fails to resolve or resolves to a manifest whose signature cannot be verified against the claimed governance platform's published key. Level 3 raises the mitigation to the TLS handshake via . Implementations SHOULD retrieve and verify the manifest for any Agent-ID carrying scope beyond read-only query operations. Mandatory Level 1 logging provides an anomaly-detection baseline for deployments that perform no active verification on every request.

Authority Laundering Threat: An agent claims an Authority-Scope broader than what it was granted. Mitigation: server-side scope enforcement; 455 Scope Violation (reason scope-claim-invalid) returned and logged. In DELEGATE chains, each hop's scope MUST be a strict subset of the delegating agent's scope.

Delegation Sequence Poisoning Threat: A malicious agent inserts itself into a Delegation Sequence, substitutes a parent (parent swap), widens its granted scope, or extends a sequence past the point where its members remain authorized. Mitigation: the per-hop verification of : parent re-verification catches the swap, attenuation checked at verify catches the widening, membership catches the revoked or inactive member, and depth and cycle limits bound the sequence. Each hop MUST also be logged with the delegating Agent-ID, the delegate Agent-ID, and the granted scope, so the sequence can be reconstructed for audit from the hop records and compared with the prior_actions chain of . Single-server reconstruction depends on the server's own records; reconstruction a distrusted holder cannot tamper with depends on inclusion in a transparency log per . Token signatures verify under keys published in the identity document; line-rate verification at an SEP requires .

Revocation Continuity (Planned) Revocation reaches a verifier through three boundaries with three clocks: certificate validity (), session lifetime (), and agent lifecycle state (the lifecycle methods of ). This revision specifies one piece of the continuity: a member of a Delegation Sequence whose lifecycle state is no longer Active fails verification on the next request (). A single specification of revocation reaching every verifier by effect time, across all three boundaries, is planned, in this document or as a companion.

Attribution-Record Tamper Evidence An Attribution-Record is produced and held by the agent whose action it records. Against a verifier that trusts the holder, the signature and the per-agent hash chain of suffice. Against a verifier that distrusts the holder, the record is tamper-evident only when it is included in a transparency log per and the inclusion proof is checked. This document states the dependency; the mechanism is inherited from those two companions.

Denial of Service via High-Frequency Agent Traffic Threat: Agents that are compromised, misconfigured, or adversarial generate extremely high request volumes. Mitigation: 429 Rate Limited status code. Rate limiting SHOULD be applied per Agent-ID and per resolved principal identifier (obtained from the agent identity document referenced by Agent-ID). When is deployed, per-Agent-ID quotas can be cryptographically tied to verified identity, preventing quota evasion through Agent-ID spoofing.

Session Hijacking Threat: An attacker intercepts or forges a Session-ID. Mitigation: mandatory TLS protects sessions in transit. Session-IDs MUST be cryptographically random with minimum 128 bits of entropy. Servers MUST validate that Session-ID, Agent-ID, and TLS client identity are consistent.

Escalation Suppression Threat: A compromised agent or intermediary suppresses ESCALATE requests, preventing human oversight. Mitigation: compliant implementations MUST route ESCALATE requests directly to the declared escalation handler without modification. Intermediaries MUST NOT drop, delay, or modify ESCALATE requests. Escalation handlers SHOULD implement independent receipt confirmation.

Agent Genesis Spoofing Threat: A malicious actor fabricates an Agent Genesis to claim a legitimate agent's identity or construct a false identity with elevated trust. Mitigation: Agent Genesis documents are issued only by governance platforms that have completed one of the three Tier 1 verification paths (). For dns-anchored registrations, the governance platform MUST verify DNS ownership of the claimed org_domain before issuance. For log-anchored registrations, the governance platform MUST submit the Agent Genesis to a transparency log per / and record the inclusion proof in the registry; tampering with a log-anchored Agent Genesis is detectable by any party with log access. For hybrid registrations, both DNS and blockchain address ownership are verified. In the base spec, mandatory logging provides auditability. Full mitigation requires for cryptographically bound Agent Genesis verification at the TLS layer. Governance platforms MUST treat any ACTIVATE request whose computed canonical Agent-ID matches an existing registry record as a collision attack and MUST reject it.

Domain Transfer Identity Hijacking Threat: An attacker acquires an expired domain to inherit the agent registry and trust history of prior registrants. Mitigation applies to dns-anchored and hybrid Tier 1 agents: agents under an expired domain are automatically Suspended within 24 hours of domain expiry detection. A new owner of the domain MUST NOT inherit prior agent registrations. See for the full domain expiry policy. log-anchored Tier 1 agents are unaffected by this threat because their verification evidence is the transparency log inclusion proof, with no DNS ownership involved.

Attribution Forgery Threat: A malicious agent submits a fabricated or replayed Attribution-Record to claim credit for an action another party performed, or to conceal the true execution context of an action it did perform. Mitigation: Attribution-Records used for accountability or admission to an audit trail MUST be signed with the agent's governance key. The signature MUST cover the full record including the Task-ID, Agent-ID, method, timestamp, and result hash. When is deployed, the signature is verified at the TLS layer against the agent's X.509 certificate. For high-stakes domains, RATS attestation evidence in the Attribution-Record per provides hardware-rooted proof of execution context that cannot be forged without compromising the attesting environment itself. Attribution-Record signatures MUST be verified before the record is admitted to an audit trail. Unverified records MUST be logged with a signature_unverified flag and MUST NOT be treated as authoritative for compliance purposes. The alg: none fallback permitted on the Attribution-Record response header () exists to preserve wire format and Audit-ID chain construction in development and transition deployments that have yet to provision a manifest signing key. An alg: none record carries no anti-forgery claim. Consumers MUST treat alg: none records as equivalent to unverified records for the purposes of this mitigation: they MUST NOT be admitted to an audit trail as authoritative, and they MUST NOT satisfy any accountability requirement that depends on cryptographic signing. Production deployments MUST configure a manifest signing key.

Privacy Considerations Agent identity carried on requests, and the agent identity document referenced by Agent-ID, carry information about agent behavior that may be sensitive:

Agent-ID together with the resolved principal identifier may reveal organizational structure
Session-ID and Task-ID reveal workflow patterns
Delegation-Chain reveals multi-agent architecture

AGTP logs containing these fields MUST be treated as sensitive operational data. Operators MUST implement appropriate access controls, retention limits, and data minimization practices consistent with applicable privacy regulations. Where privacy-preserving attribution is required, implementations MAY use pseudonymous Agent-IDs with a separate trusted resolution service. The architecture for pseudonymous agent identity resolution is reserved for a future companion document.

Denial-of-Service Considerations AGTP's agent identity provides a mechanism for more precise denial-of-service mitigation than is possible with HTTP. Rate limiting SHOULD be applied per Agent-ID and per resolved principal identifier (obtained from the agent identity document) in addition to per-IP-address controls. When is deployed, per-Agent-ID rate limiting can be cryptographically tied to verified agent identity, preventing quota evasion through Agent-ID rotation. Implementations planning high-volume governed agent deployments SHOULD plan for as part of their denial-of-service mitigation strategy. Additional recommended mitigations: traffic-shaping by request class once the Priority header is normatively specified (reserved for v01+ per ); and circuit breaker patterns for ESCALATE request floods.

Intellectual Property Considerations The core AGTP specification, including all base methods, header fields, status codes, connection model, and IANA registrations defined in this document, is intended for open implementation without royalty obligation. Certain elements referenced in this document may be subject to pending patent applications by the author, specifically:

The Agent Certificate extension , which provides cryptographic binding of agent identity and authority scope to AGTP header fields.
The ACTIVATE method, which provides AGTP-native transmission and activation of governed agent packages.
The Agent Genesis mechanism (), which provides the genesis identity record and canonical Agent-ID derivation process for AGTP-registered agents.
The .agent file format specification, an open packaging format for AI agents.
The .nomo file format specification, a governed packaging format for AI agents with cryptographic governance binding.

Implementers of the core AGTP specification are unaffected by any intellectual property claims on these extensions and associated formats. The licensor is prepared to grant a royalty-free license to implementers for any patent claims that cover contributions in this document and its referenced extensions, consistent with the IETF's IPR framework under . IPR disclosures have been filed with the IETF Secretariat and are available at: https://datatracker.ietf.org/ipr/

IANA Considerations This document records the following IANA registrations.

Port Assignment The following service names and port number are registered in the IANA Service Name and Transport Protocol Port Number Registry per : AGTP Port Assignments

Service Name	Port	Transport	Description
agtp	4480	TCP	Agent Transfer Protocol over TCP/TLS
agtp-quic	4480	UDP	Agent Transfer Protocol over QUIC

The unified port assignment (4480 for both TCP and UDP under a single conceptual agtp service) follows the precedent set by HTTPS (443/TCP and 443/UDP for HTTP/3). The transport is distinguished at the protocol level; the port number alone decides nothing.

Contact:: Chris Hood, chris@nomotic.ai
Reference:: This document

AGTP Method Registry Establishment of an IANA registry: Agent Transfer Protocol Methods.

Registry name:: Agent Transfer Protocol Methods
Registration procedure:: Expert Review per , with the additional requirement that each registration be accompanied by a published specification, at minimum a publicly available Internet-Draft or equivalent document. The Designated Expert SHOULD verify that the proposed method name is unique, the reference specification is publicly accessible, the method definition includes the required fields (parameters, response structure, idempotency, error codes, security considerations), and the method conforms to the AGTP-METHODS specification .
Reference:: This document

Initial registrations (the eighteen-method protocol floor): Initial AGTP Method Registry Entries (Eighteen-Method Floor)

Method	Group	Status
QUERY	Cognitive	Permanent
DISCOVER	Cognitive	Permanent
DESCRIBE	Cognitive	Permanent
INSPECT	Cognitive	Permanent
SUMMARIZE	Cognitive	Permanent
PLAN	Cognitive	Permanent
PROPOSE	Cognitive	Permanent
EXECUTE	Mechanics	Permanent
DELEGATE	Mechanics	Permanent
ESCALATE	Mechanics	Permanent
CONFIRM	Mechanics	Permanent
SUSPEND	Mechanics	Permanent
NOTIFY	Mechanics	Permanent
ACTIVATE	Lifecycle	Permanent
DEACTIVATE	Lifecycle	Permanent
REINSTATE	Lifecycle	Permanent
REVOKE	Lifecycle	Permanent
DEPRECATE	Lifecycle	Permanent

The methods BOOK, SCHEDULE, LEARN, and COLLABORATE, present in the v06 core set, are demoted in v07 to Tier 2 standard extended methods and are registered through the AGTP-METHODS method catalog (); this document registers the floor only.

AGTP Status Code Registry Establishment of an IANA registry: Agent Transfer Protocol Status Codes.

Registry name:: Agent Transfer Protocol Status Codes
Registration procedure:: Expert Review + published specification required.

AGTP-specific status code numbers are chosen from ranges unassigned in the IANA HTTP Status Code Registry to avoid semantic collision with HTTP status codes that may appear in payloads carried by AGTP method invocations. Two status codes used by AGTP retain their HTTP code numbers (408 and 410) but carry AGTP-specific semantics. They are registered here with text describing the AGTP semantic. The following AGTP status codes are registered with full definitions: AGTP-Specific Status Code Definitions

Code	Name	Definition
261	Negotiation In Progress	The service has received a PROPOSE request and is evaluating it asynchronously. The response body MUST include a `proposal_id` and an estimated evaluation duration. The agent retrieves the terminal status by invoking `QUERY /proposals/{proposal_id}` until a 263 (Proposal Approved) or 463 (Proposal Rejected) response is returned. Server policy controls whether async evaluation is offered.
262	Authorization Required	Authorization the agent could obtain is absent: credential establishment, consent, or an unclaimed scope its identity document grants. Never used when the request exceeds held authority (455). The response body MUST specify which authorization condition applies: `scope-required` (the endpoint requires Authority-Scope the agent has yet to declare), `wildcards-required` (the request is an ad-hoc method invocation and the wildcards consent on either the agent identity document or the server policy is absent), `credentials-missing` (the server requires credentials such as AGTP-CERT or OAuth-scoped token before evaluating the request), or `anonymous-discovery-disabled` (the server requires authenticated identity for manifest retrieval and the request is unauthenticated). Returned for PROPOSE-time authorization, endpoint-dispatch scope checks, ad-hoc invocation wildcards refusal, and discovery requests blocked by policy.
263	Proposal Approved	The service has accepted the PROPOSE request and instantiated the proposed endpoint. The response body MUST contain a complete AGTP-METHODS endpoint definition for the instantiated endpoint, a `synthesis_id` identifying the synthesized endpoint for follow-on invocation, and `expires_at` indicating when the synthesis expires. MAY include a `persistent` boolean and `granted_duration` indicating the actual duration the server granted (which may be less than the agent requested, bounded by server policy).
405	Method Not Allowed	The method is recognized and the path is valid, but the server's policy or registry exposes no endpoint at that combination. The response body MUST list allowed methods for the path and any redirects from the manifest's `policies.methods` sub-block. The agent MAY PROPOSE the combination when policy is the only obstacle.
408	Timeout	The method's declared TTL expired before execution completed. AGTP-specific semantics distinct from HTTP's request-timeout: applies to the AGTP method TTL, a different clock from the transport request timeout. MUST be logged.
410	Gone	The Agent-ID is permanently retired through REVOKE of the underlying Agent Genesis. AGTP-specific semantics distinct from HTTP's resource-removed: applies to permanent identity retirement. A Deprecated agent does NOT return 410 and continues to serve traffic; deprecation signals planned end-of-life while the agent remains in service. The canonical Agent-ID of a retired agent MUST NOT be retried.
455	Scope Violation	The request exceeds the authority the agent holds (Authority-Scope claim beyond grant, endpoint scope ungranted, delegation beyond parent) or an operator-defined scope dimension other than rate-limit, budget, or zone (dedicated codes 429, 456, 457). Typical applications include token-based scope violations and query-based scope violations where the operator defines a scope dimension outside the standard set. The server MUST log this event. The agent MUST NOT retry the same request without modifying its scope declaration. Governance signal, distinct from a protocol error.
456	Budget Exceeded	The requested method execution would exceed the resource limits declared in the Budget-Limit request header. The agent MUST NOT retry without modifying the Budget-Limit or reducing request scope. Governance signal; MUST be logged.
457	Zone Violation	The request would route outside the network boundary declared in the AGTP-Zone-ID header. SEP-enforced. The agent MUST NOT retry without modifying the AGTP-Zone-ID or obtaining explicit cross-zone authorization. MUST be logged.
458	Counterparty Unverified	The merchant counterparty in a PURCHASE invocation failed identity verification. Returned when the `Merchant-ID` or `Merchant-Manifest-Fingerprint` request headers are absent, when the fingerprint differs from the receiving server's current Merchant Manifest Document, when the Merchant-ID differs from the server's canonical ID, or when the merchant is in a non-Active lifecycle state. Governance signal; MUST be logged. Full definition in .
459	Method Violation	The method name is absent from the AGTP-METHODS approved method catalog. The method itself is the problem. The response body MUST identify the unrecognized method and SHOULD reference the AGTP-METHODS method catalog version in effect. The agent MUST select a different method before retrying, or MAY PROPOSE the method if no suitable replacement exists.
460	Endpoint Violation	The endpoint path violates AGTP-METHODS path grammar. A path segment matches an approved method name (case-insensitive), indicating method-name leakage into the path. The response body MUST identify the offending path segment. The agent MUST restructure the path before retrying.
461	RCNS Contract Available	The requested endpoint is unregistered but the server is prepared to synthesize a contract for it. The response body MUST carry a contract preview including the resolved method, path, and `synthesis_id`; the caller MAY accept the contract by re-issuing the request with the `Contract-Synthesized` header or decline by ignoring the response. Returned in the confirm-first RCNS delivery mode per .
462	Insufficient Budget	Commerce request budget envelope is insufficient for the receiving agent's pricing tier or settlement requirements. Returned when a caller's Budget-Limit header is below the receiving agent's published price for the requested method/scope, or when the declared settlementMethod matches none of the receiver's accepted settlement endpoints. Full definition in .
463	Proposal Rejected	The service cannot or declines to instantiate the proposed endpoint. Returned in response to PROPOSE. The response body MUST include a structured `reason` field with one of the values `out-of-scope`, `policy-refused`, `composition-impossible`, `ambiguous`, or `synthesis-disabled`, an `explanation` string, and MAY include an optional `counter_proposal` suggesting a related endpoint the server would accept.
464	RCNS No Contract	An RCNS synthesis attempt was made but no contract could be delivered. The response body MUST include a structured `reason` field with one of the values `rcns-disabled`, `trust-tier-insufficient`, `composition-impossible`, `synthesis-error`, `contract-not-yours`, or `contract-revoked`, and an `explanation` string. See .
465	Reserved	Reserved for AGTP expansion.
550	Delegation Failure	A sub-agent to which a task was delegated via the DELEGATE method failed to complete the task within the declared deadline or returned an error. The response body SHOULD contain the sub-agent's error details.
551	Authority Chain Broken	The Delegation Sequence carried in the `Delegation-Chain` header fails verification: membership, parent re-verification, attenuation, freshness, depth, or cycle check. The response body MUST carry the `reason` token and the index of the failing hop. The server MUST log this event.
552	Reserved	Reserved for AGTP expansion.
553	Reserved	Reserved for AGTP expansion.
554	Reserved	Reserved for AGTP expansion.
555	Reserved	Reserved for AGTP expansion.

Media Type Registry This section is the master registry of all AGTP-family media types. Types defined by companion specifications are listed here for cross-document discoverability; their normative definitions remain in the defining document. AGTP Media Type Registrations

Media Type	Use	IANA Status
`application/vnd.agtp+json`	AGTP method request/response bodies (JSON)	Planned (this document)
`application/vnd.agtp+yaml`	AGTP method request/response bodies (YAML)	Planned (this document)
`application/vnd.agtp.identity+json`	Agent Identity Document (JSON)	Registered (vendor tree)
`application/vnd.agtp.identity+yaml`	Agent Identity Document (YAML)	Registered (vendor tree)
`application/vnd.agtp.manifest+json`	AGTP server manifest	Planned (AGTP-METHODS)
`application/vnd.agtp.endpoint+json`	AGTP-METHODS endpoint definition	Planned (AGTP-METHODS)
`application/agtp-pricing+json`	AGTP commerce pricing manifest	Planned (AGTP-COMMERCE)

"Registered (vendor tree)" indicates that IANA registration is complete in the application/vnd.* vendor tree as of the date of this revision. "Planned (this document)" and "Planned (companion document)" indicate types for which registration applications will be filed concurrent with publication of the defining document. Standards-tree promotion of the full set is anticipated at RFC publication of the AGTP family.

Header Field Registry AGTP header fields are distinct from HTTP header fields and are registered in a new IANA registry: Agent Transfer Protocol Header Fields.

Registry name:: Agent Transfer Protocol Header Fields
Registration procedure:: Expert Review + published specification required.

AGTP keeps its own registry, separate from the HTTP Field Name Registry, as AGTP header fields have different semantics, applicability, and versioning constraints from HTTP fields. HTTP header fields carry no automatic validity in AGTP, and AGTP header fields are invalid as HTTP fields. Initial registrations (all Permanent): Agent-ID, Owner-ID, Authority-Scope, Session-ID, Task-ID, Delegation-Chain, Server-ID, Attribution-Record, Continuation-Token, Supported-Methods, Cost-Estimate, Attestation-Evidence, Authorization, Merchant-ID, Merchant-Manifest-Fingerprint, Intent-Assertion, Cart-Digest, AGTP-Methods-Version, AGTP-Catalog-Warning, AGTP-Endpoint-Warning, Allow-RCNS. The four merchant-related headers are defined in and registered concurrently with this document. The three catalog-related headers (AGTP-Methods-Version, formerly AGTP-API-Version, AGTP-Catalog-Warning, and AGTP-Endpoint-Warning) are defined in and registered concurrently. The Authorization header semantics for composition with external identity providers are specified in . The Allow-RCNS header semantics for caller opt-in to Runtime Contract Negotiation are specified in . Planned headers (Priority, TTL, AGTP-Zone-ID, Telemetry-Export) are unregistered in this revision. They will be registered alongside the revision that specifies their normative semantics. Content-Schema is registered by . The Budget-Limit header is defined in and registered concurrently with that document.

URI Scheme Registration The agtp:// URI scheme is registered per . Full registration template is documented in .

AGTP Budget Unit Registry Establishment of a new IANA sub-registry: Agent Transfer Protocol Budget Units.

Registry name:: Agent Transfer Protocol Budget Units
Registration procedure:: Expert Review per . New unit registrations MUST define: unit name (lowercase ASCII, no spaces or special characters), semantic description, value format (integer or decimal), whether fractional values are permitted, and a reference specification. Units representing financial denominations MUST specify the currency and MUST define precision (decimal places). The Designated Expert SHOULD verify that the proposed unit duplicates no existing registration and that the value format is unambiguous.
Reference:: This document

Initial registrations: Initial AGTP Budget Unit Registry Entries

Unit	Description	Value Format	Fractional
tokens	Language model token consumption	Integer	No
compute-seconds	CPU/GPU compute time in seconds	Decimal	Yes
USD	US Dollar financial limit	Decimal, 2 places	Yes
EUR	Euro financial limit	Decimal, 2 places	Yes
GBP	Pound Sterling financial limit	Decimal, 2 places	Yes
calls	Downstream API call count	Integer	No

Agent Registry Retention Policy The AGTP registry MUST retain records for all registered agents regardless of lifecycle state. The following minimum retention periods apply: AGTP Registry Minimum Retention Periods

Lifecycle State	Minimum Retention Period
Active	Duration of Active state + 7 years
Suspended	Duration of Suspended state + 7 years
Revoked	10 years from revocation date
Deprecated	7 years from deprecation date

The 7-year minimum reflects common enterprise compliance requirements (SOX, GDPR audit trails, HIPAA). Governance platform operators in regulated industries SHOULD extend these minimums to match applicable regulatory requirements. The retained record for a Revoked or Deprecated agent MUST include:

Canonical Agent-ID (permanently retired, never reissued)
Agent label and org domain at time of registration
Trust tier at time of registration
Activation date and activating principal
Revocation or deprecation date, initiating principal, and reason code
Genesis audit record hash (pointer to immutable audit log)
Full Agent Genesis (archived, inaccessible to the public)
All lifecycle state transitions with timestamps

The retained record MUST NOT contain package executable contents, active session data, or Authority-Scope grant tokens.

Domain Name Expiry Interaction If an organization's org_domain expires or transfers to a new owner:

All Active agents registered under the expired domain MUST be automatically Suspended within 24 hours of domain expiry detection.
The governance platform MUST notify the registered principal contact before suspension takes effect, with a minimum notice period of 30 days if domain expiry was predictable.
Suspended agents under an expired domain transition to Deprecated state after 90 days if the domain is still expired.
A new owner of the domain MUST NOT inherit prior agent registrations. New ACTIVATE transactions are required.

This policy prevents domain-transfer-based identity hijacking in which an attacker acquires an expired domain to claim the trust history of agents that operated under it.

References Normative References Key words for use in RFCs to Indicate Requirement Levels In many standards track documents several words are used to signify the requirements in the specification. These words are often capitalized. This document defines these words as they should be interpreted in IETF documents. This document specifies an Internet Best Current Practices for the Internet Community, and requests discussion and suggestions for improvements. Ambiguity of Uppercase vs Lowercase in RFC 2119 Key Words RFC 2119 specifies common key words that may be used in protocol specifications. This document aims to reduce the ambiguity by clarifying that only UPPERCASE usage of the key words have the defined special meanings. Uniform Resource Identifier (URI): Generic Syntax A Uniform Resource Identifier (URI) is a compact sequence of characters that identifies an abstract or physical resource. This specification defines the generic URI syntax and a process for resolving URI references that might be in relative form, along with guidelines and security considerations for the use of URIs on the Internet. The URI syntax defines a grammar that is a superset of all valid URIs, allowing an implementation to parse the common components of a URI reference without knowing the scheme-specific requirements of every possible identifier. This specification does not define a generative grammar for URIs; that task is performed by the individual specifications of each URI scheme. [STANDARDS-TRACK] Internet Assigned Numbers Authority (IANA) Procedures for the Management of the Service Name and Transport Protocol Port Number Registry This document defines the procedures that the Internet Assigned Numbers Authority (IANA) uses when handling assignment and other requests related to the Service Name and Transport Protocol Port Number registry. It also discusses the rationale and principles behind these procedures and how they facilitate the long-term sustainability of the registry. This document updates IANA's procedures by obsoleting the previous UDP and TCP port assignment procedures defined in Sections 8 and 9.1 of the IANA Allocation Guidelines, and it updates the IANA service name and port assignment procedures for UDP-Lite, the Datagram Congestion Control Protocol (DCCP), and the Stream Control Transmission Protocol (SCTP). It also updates the DNS SRV specification to clarify what a service name is and how it is registered. This memo documents an Internet Best Current Practice. JSON Web Signature (JWS) JSON Web Signature (JWS) represents content secured with digital signatures or Message Authentication Codes (MACs) using JSON-based data structures. Cryptographic algorithms and identifiers for use with this specification are described in the separate JSON Web Algorithms (JWA) specification and an IANA registry defined by that specification. Related encryption capabilities are described in the separate JSON Web Encryption (JWE) specification. Well-Known Uniform Resource Identifiers (URIs) This memo defines a path prefix for "well-known locations", "/.well-known/", in selected Uniform Resource Identifier (URI) schemes. In doing so, it obsoletes RFC 5785 and updates the URI schemes defined in RFC 7230 to reserve that space. It also updates RFC 7595 to track URI schemes that support well-known URIs in their registry. QUIC: A UDP-Based Multiplexed and Secure Transport This document defines the core of the QUIC transport protocol. QUIC provides applications with flow-controlled streams for structured communication, low-latency connection establishment, and network path migration. QUIC includes security measures that ensure confidentiality, integrity, and availability in a range of deployment circumstances. Accompanying documents describe the integration of TLS for key negotiation, loss detection, and an exemplary congestion control algorithm. HTTP Semantics The Hypertext Transfer Protocol (HTTP) is a stateless application-level protocol for distributed, collaborative, hypertext information systems. This document describes the overall architecture of HTTP, establishes common terminology, and defines aspects of the protocol that are shared by all versions. In this definition are core protocol elements, extensibility mechanisms, and the "http" and "https" Uniform Resource Identifier (URI) schemes. This document updates RFC 3864 and obsoletes RFCs 2818, 7231, 7232, 7233, 7235, 7538, 7615, 7694, and portions of 7230. Internet X.509 Public Key Infrastructure Certificate and Certificate Revocation List (CRL) Profile This memo profiles the X.509 v3 certificate and X.509 v2 certificate revocation list (CRL) for use in the Internet. An overview of this approach and model is provided as an introduction. The X.509 v3 certificate format is described in detail, with additional information regarding the format and semantics of Internet name forms. Standard certificate extensions are described and two Internet-specific extensions are defined. A set of required certificate extensions is specified. The X.509 v2 CRL format is described in detail along with standard and Internet-specific extensions. An algorithm for X.509 certification path validation is described. An ASN.1 module and examples are provided in the appendices. [STANDARDS-TRACK] Guidelines for Writing an IANA Considerations Section in RFCs Many protocols make use of points of extensibility that use constants to identify various protocol parameters. To ensure that the values in these fields do not have conflicting uses and to promote interoperability, their allocations are often coordinated by a central record keeper. For IETF protocols, that role is filled by the Internet Assigned Numbers Authority (IANA). To make assignments in a given registry prudently, guidance describing the conditions under which new values should be assigned, as well as when and how modifications to existing values can be made, is needed. This document defines a framework for the documentation of these guidelines by specification authors, in order to assure that the provided guidance for the IANA Considerations is clear and addresses the various issues that are likely in the operation of a registry. This is the third edition of this document; it obsoletes RFC 5226. Intellectual Property Rights in IETF Technology The IETF policies about Intellectual Property Rights (IPR), such as patent rights, relative to technologies developed in the IETF are designed to ensure that IETF working groups and participants have as much information as possible about any IPR constraints on a technical proposal as early as possible in the development process. The policies are intended to benefit the Internet community and the public at large, while respecting the legitimate rights of IPR holders. This document sets out the IETF policies concerning IPR related to technology worked on within the IETF. It also describes the objectives that the policies are designed to meet. This document updates RFC 2026 and, with RFC 5378, replaces Section 10 of RFC 2026. This document also obsoletes RFCs 3979 and 4879. Remote ATtestation procedureS (RATS) Architecture In network protocol exchanges, it is often useful for one end of a communication to know whether the other end is in an intended operating state. This document provides an architectural overview of the entities involved that make such tests possible through the process of generating, conveying, and evaluating evidentiary Claims. It provides a model that is neutral toward processor architectures, the content of Claims, and protocols. JSON Canonicalization Scheme (JCS) Cryptographic operations like hashing and signing need the data to be expressed in an invariant format so that the operations are reliably repeatable. One way to address this is to create a canonical representation of the data. Canonicalization also permits data to be exchanged in its original form on the "wire" while cryptographic operations performed on the canonicalized counterpart of the data in the producer and consumer endpoints generate consistent results. This document describes the JSON Canonicalization Scheme (JCS). This specification defines how to create a canonical representation of JSON data by building on the strict serialization methods for JSON primitives defined by ECMAScript, constraining JSON data to the Internet JSON (I-JSON) subset, and by using deterministic property sorting. AGTP Methods (AGTP Verbs): Method Vocabulary, Path Grammar, and Endpoints AGTP-RCNS: Runtime Contract Negotiation Substrate AGTP Agent Identity Document AGTP Identifier Chain Informative References HTTP/3 The QUIC transport protocol has several features that are desirable in a transport for HTTP, such as stream multiplexing, per-stream flow control, and low-latency connection establishment. This document describes a mapping of HTTP semantics over QUIC. This document also identifies HTTP/2 features that are subsumed by QUIC and describes how HTTP/2 extensions can be ported to HTTP/3. Hypertext Transfer Protocol Version 2 (HTTP/2) This specification describes an optimized expression of the semantics of the Hypertext Transfer Protocol (HTTP), referred to as HTTP version 2 (HTTP/2). HTTP/2 enables a more efficient use of network resources and a reduced perception of latency by introducing header field compression and allowing multiple concurrent exchanges on the same connection. It also introduces unsolicited push of representations from servers to clients. This specification is an alternative to, but does not obsolete, the HTTP/1.1 message syntax. HTTP's existing semantics remain unchanged. The OAuth 2.0 Authorization Framework The OAuth 2.0 authorization framework enables a third-party application to obtain limited access to an HTTP service, either on behalf of a resource owner by orchestrating an approval interaction between the resource owner and the HTTP service, or by allowing the third-party application to obtain access on its own behalf. This specification replaces and obsoletes the OAuth 1.0 protocol described in RFC 5849. [STANDARDS-TRACK] JSON Web Token (JWT) JSON Web Token (JWT) is a compact, URL-safe means of representing claims to be transferred between two parties. The claims in a JWT are encoded as a JSON object that is used as the payload of a JSON Web Signature (JWS) structure or as the plaintext of a JSON Web Encryption (JWE) structure, enabling the claims to be digitally signed or integrity protected with a Message Authentication Code (MAC) and/or encrypted. Guidelines and Registration Procedures for URI Schemes This document updates the guidelines and recommendations, as well as the IANA registration processes, for the definition of Uniform Resource Identifier (URI) schemes. It obsoletes RFC 4395. Certificate Transparency Version 2.0 This document describes version 2.0 of the Certificate Transparency (CT) protocol for publicly logging the existence of Transport Layer Security (TLS) server certificates as they are issued or observed, in a manner that allows anyone to audit certification authority (CA) activity and notice the issuance of suspect certificates as well as to audit the certificate logs themselves. The intent is that eventually clients would refuse to honor certificates that do not appear in a log, effectively forcing CAs to add all issued certificates to the logs. This document obsoletes RFC 6962. It also specifies a new TLS extension that is used to send various CT log artifacts. Logs are network services that implement the protocol operations for submissions and queries that are defined in this document. An Architecture for Trustworthy and Transparent Digital Supply Chains Traceability in supply chains is a growing security concern. While Verifiable Data Structures (VDSs) have addressed specific issues, such as equivocation over digital certificates, they lack a universal architecture for all supply chains. This document defines such an architecture for single-issuer signed statement transparency. It ensures extensibility and interoperability between different transparency services as well as compliance with various auditing procedures and regulatory requirements. Agent-to-Agent Protocol Specification Linux Foundation Agent Communication Protocol IBM Research Model Context Protocol Anthropic Agent Network Protocol AGTP Agent Certificate Extension Semantic Method Naming and LLM Agent Accuracy: A Controlled Benchmark of REST/CRUD versus Agentive API Interface Design AGTP Communication Protocol AGTP Session Protocol AGTP-API: Verbs, Paths, Endpoints, and Synthesis AGTP Discovery and Naming AGTP Composition Profiles AGTP Transport Bindings: TCP/TLS and QUIC AGTP Merchant Identity and Agentic Commerce Binding AGTP Transparency Log Protocol AGTP Trust and Verification Specification AGTP Presence: Ambient Discovery and Visibility for Agents AGTP Binding to the Legal Entity Identifier (LEI and vLEI) AGTP-Commerce: Open Commerce Specification for Agent-to-Agent Transactions

Changes from v09 Version 10 is a structural and language revision with one new normative mechanism.

Substantive Changes

Delegation-Chain specified. The header reserved since v00 is specified (): format (ordered hops of canonical Agent-ID and delegation token), minting at DELEGATE under the existing strict-subset rule, per-hop verification (membership, parent re-verification, attenuation, freshness, depth and cycle), the effective scope as the accepted result, and 551 failure behavior with a reason vocabulary. Terminology distinguishes the Delegation Sequence (the hops) from the Delegation-Chain header (its carrier). The composition table, the worked DELEGATE example, and the security considerations are aligned to the specification; earlier revisions described the header as if specified in those places while reserving it in the header table.
Delegation token format and authority evidence. The hop token payload is specified () with a digest of the parent token, so a parent swap fails on the digest as well as the key. Verification is defined over a fixed input set with no local policy and returns valid, invalid, or indeterminate (); an origin hop may reference an authority assertion for the delegator's own powers (); and a table states what each artifact in a delegated request asserts ().
Structured failure fields. retryable, partial with completed_steps, side_effects, and reason on 4xx and 5xx bodies (). Additive.
Specification status vocabulary. Specified, specified and implemented, planned, inherited (), with the carrier-versus-claim rule stated. Applied through the document.
Transfer protocol. AGTP is described as a transfer protocol throughout; "transport" now refers only to TCP, TLS, and QUIC. The positioning section is rewritten around the HTTP and HTML analogy in place of SMTP and TCP.
Revocation continuity and tamper evidence stated as planned and inherited respectively ( and the following subsection), with the member-inactive check of as the first specified piece.
Tool and resource identity stated as a deliberate composition choice under review ().
Workload and agent identity composition sentence added to Identity at the Wire, and a Discovery and Naming subsection added to Related Work carrying the identity and location split and the discover versus search vocabulary.
Per-request proof of possession. The Request-Signature header () binds every non-anonymous request to the agent's current signing key, published as agent_public_key in the Identity Document. Level 2 verification gains a fifth step and now establishes the sender as well as the document; a verifier that skips the step is at Level 1 for every purpose that depends on who sent the request. Answers the self-asserted-identity finding raised independently by four reviewers and conceded on list in August.
262 versus 455 resolved. Obtainability is the rule: 262 when the agent could obtain the missing authorization, 455 when the request exceeds authority the agent holds. A claimed scope beyond the document's grant, an endpoint scope the document fails to grant, and a delegation beyond the parent are all 455. Earlier revisions used both codes for Authority-Scope failures in different sections.
HTTP registry argument withdrawn. The claim that IETF Review freezes the HTTP method registry is removed; the case rests on the distinct wire image and the documented failure cases.
WIMSE chain convention mapping and a stated staleness bound ().
Governance Token action digest binding a token to one request shape, with token-action-mismatch on divergence.
evaluation failure field distinguishing a refusal from an incomplete check, with missing_input.
User agent and service agent stated as both in scope, with the Owner-ID as what differs.

Structural Changes

AGTP-API replaced by AGTP-METHODS and AGTP-RCNS. Every reference to is redirected: the method vocabulary, path grammar, endpoint primitive, manifest, and policy to ; negotiation, contracts, and synthesis to . The AGTP-API-Version header registration is renamed AGTP-Methods-Version.
Agent Identity Document extracted. The Agent Namespace Document, the Agent Identity Document and .agtp format, and the browser interaction model move to ; this document keeps a summary () stating what the protocol depends on. The Agent Genesis, registration lifecycle, and lifecycle events remain here because the Agent-ID derivation and the lifecycle methods depend on them.
Module summaries. Dynamic Endpoint Negotiation, the Extended Method Vocabulary, Composition Profiles, and the Merchant Identity sections are reduced to summaries that point at the companion carrying the normative text. The AGMP wire example appendix moves to .
Change history collapsed. The v06, v07, and v08 change logs (about 680 lines) are replaced by ; the full text remains in the archived revisions.
Glossary merged into Terminology; four entries that appeared only in the glossary are carried over.
Agent defined operationally. The Terminology entry for Agent now states what the protocol can enforce (Genesis-issued Agent-ID, principal and scope, per-request proof of possession, attributable actions) in place of the v09 description of an AI software system acting without supervision. The protocol has no knowledge of how a participant is implemented; it constrains and attributes what the participant does.
DISCOVER and ACTIVATE aligned with the companions. DISCOVER now distinguishes search (criteria to candidates) from discovery (Agent-ID to attachment) per and defers its parameter set and response shape there; the v09 parameter table (criteria, filter, max_results, context) disagreed with the companion and is withdrawn. ACTIVATE is named as the publish event: ANS registration () and the first ANNOUNCE () follow from the lifecycle transition, so an agent is findable exactly when Active.
Agent-ID hash excludes log_inclusion_proof. The Genesis hash that yields the Canonical Agent-ID now excludes the inclusion proof alongside signature, so that a log-anchored issuer can compute the Agent-ID, commit it, and embed the receipt without the identity changing; v09's rule was circular with the statement subject in . log_uri is added to the Genesis fields as that document proposed. Compatibility: only Genesis documents that carry a non-null log_inclusion_proof hash differently; dns-anchored and org-asserted Genesis documents whose field is absent are unaffected, and a document that carried the field as null MUST be re-hashed by its issuer under the v10 rule before it is served as v10. The registration section's remaining references to issuance "at ACTIVATE time" are corrected to registration, matching the ACTIVATE definition.
Planned-header table relabeled in the status vocabulary of : Budget-Limit is specified in and Content-Schema in ; Priority, TTL, AGTP-Zone-ID, and Telemetry-Export are planned. The v09 label "Reserved (v01+)" was stale.

Wire Format Compatibility The Delegation-Chain header changes from reserved to specified. A v09 server receiving it MAY have rejected it with 501; a v10 server verifies it. Requests without the header are unchanged. Request-Signature is new and required on non-anonymous requests; a v10 server MUST accept unsigned requests from agents whose Identity Document predates agent_public_key under the possession-unproven rule of , so v09 agents keep working at Level 1 until re-issued. The 262 to 455 change for Authority-Scope failures is wire-visible for clients that branched on 262; clients SHOULD treat 455 with scope-claim-invalid or scope-exceeds-parent as they treated 262 scope-required. The structured failure fields and action_digest are additive. The AGTP-Methods-Version rename is advisory; servers MAY emit both names during transition. No other wire-visible behavior changes.

Change History Version 09 (June 2026) added the lifecycle method group to the embedded floor, completing the eighteen-method floor; adopted Owner-ID in place of Principal-ID, recorded in the identity document and never carried as a header; added the RCNS headers and status codes 461 and 464 with their reason vocabulary; and aligned the companion references to the v09 family. Version 08 (May 2026) expanded the floor from twelve to eighteen methods organized as cognitive, mechanics, and lifecycle groups; added trust posture headers, INSPECT read access control, lifecycle method authorization, cross-agent chain walking, signed manifests, DISCOVER path-keyed dispatch, and SCITT-aligned lifecycle receipts; and introduced the Runtime Contract Negotiation Substrate framing. Version 07 (May 2026) trimmed the header model to the request-line plus Agent-ID, Authority-Scope, Session-ID, Task-ID, and the reserved Delegation-Chain, with Server-ID and Attribution-Record on responses; adopted the comma-separated Authority-Scope grammar; removed the Birth Certificate terminology in favor of Agent Genesis; extracted trust tier detail to AGTP-TRUST; and folded AGIS and AGTP-Methods into AGTP-METHODS. Version 06 (April 2026) recorded the IANA port 4480 assignment and the agtp:// URI scheme registration. The complete change logs for these revisions are in the archived drafts at github.com/nomoticai/agtp-ietf.

Authority-Scope Format Authority-Scope values are expressed as a comma-separated list of scope tokens, each following the pattern domain:action or domain:* for full-domain access. Multi-segment scope tokens of the form domain:subdomain:action are admissible for namespaced operations (e.g., mcp:tools:execute). The encoding follows the HTTP-standard list-valued header convention : tokens are separated by a comma, with optional surrounding whitespace permitted for readability. Tokens MUST be lowercase ASCII segments separated by colons, with no internal whitespace. The wire-level grammar in ABNF: A scope token MUST contain at least two segments separated by a colon. The final segment is the action; preceding segments form the namespace path. The two-segment form domain:action is the canonical case; the three-or-more-segment form is reserved for deployments that need namespaced authority hierarchies (e.g., external-protocol bridging, hierarchical resource grants). Parsers MUST accept any amount of optional whitespace adjacent to the comma separator (including none) and MUST treat "calendar:book,calendar:query" and "calendar:book, calendar:query" as equivalent. Implementations SHOULD emit a single space after the comma for human readability. Examples: In the Agent Identity Document, Authority-Scope is represented as a JSON array of scope-token strings (one token per array element); the wire header carries a single comma-separated string. The wire-header encoding and the JSON-document encoding carry the same logical set of tokens. Reserved domains (initial set): Reserved Authority-Scope Domains

Domain	Description
calendar	Scheduling and time-based resource management
documents	Document access, summarization, and annotation
knowledge	Agent context and memory operations
booking	Reservation and resource allocation
payments	Financial transactions and confirmations
agents	Delegation and collaboration with other agents
escalation	Escalation routing and handler management
activation	Governed agent package activation (ACTIVATE method extension)
discovery	Agent discovery and capability query operations (DISCOVER, DESCRIBE)
budget	Resource budget declaration and QUOTE pre-flight operations
telemetry	Telemetry export and observability operations
zone	Network zone boundary declaration and enforcement
suspend	Session suspension and resumption operations
merchant	Merchant identity resolution and counterparty verification (see )
intent	Intent Assertion issuance and validation (see )
*	All domains require explicit grant; use with caution

Reserved Operator Tokens Two scope tokens are reserved for operators and MUST NOT appear in an agent's identity-document scope set unless the agent is the server's operator:

inspect:all:: Grants INSPECT read access across every agent the server hosts, and authorizes the operator-fired REVOKE target=stale-contracts sweep and the cross-agent DISCOVER /contracts view specified in .
rcns:negotiate:: Opens the caller-scope lock of the RCNS dispatcher gate (). Unlike inspect:all, this token MAY be granted to any agent the operator chooses to admit to runtime negotiation.

Example AGTP Wire Formats The following examples use a human-readable pseudo-wire format with HTTP-style headers followed by a JSON body. The Content-Type for all AGTP message bodies is application/vnd.agtp+json.

QUERY Request and Response

EXECUTE Request and Response (Carried Application Payload) The following example shows EXECUTE carrying an application-layer booking action. The Authority-Scope on the request governs the action; a scope mismatch would return 455.

EXECUTE Carrying an MCP Tool Invocation The following example shows EXECUTE carrying an MCP tool invocation. The carried payload's Content-Type identifies it as MCP; the AGTP server dispatches to its MCP handler. AGTP supplies identity, authority, and attribution at the wire level; MCP supplies tool semantics in the payload.

ESCALATE Request and Response

Comparison Table AGTP Compared to Existing Approaches

Criterion	AGTP	HTTP/REST	gRPC	AGMP (MCP, A2A, ...)
Intent-native methods	Yes (12 Tier 1)	No	No	Partial
Intent semantics at protocol level	Native	None	None	Messaging layer only
Built-in agent identity	Yes	No	No	No
Authority scope enforcement	Protocol-level	None	None	Application-layer
Built-in attribution/audit	Yes	No	No	Varies by impl.
Transport flexibility	TCP/UDP/QUIC	TCP/TLS	HTTP/2	HTTP
Escalation as first-class primitive	Yes	No	No	No
Ecosystem maturity	Proposed	Mature	Mature	Emerging
Governance/observability	Native	Manual/bolt-on	Manual	Limited
Method vocabulary	Intent-named, catalog of 425	Resource operations, registry extensible	N/A	N/A
Open core / royalty-free	Yes	Yes	Yes	Yes
Agent Identity Document	Native (.agtp format)	None	None	None
Tamper-proof identity surface	Yes (hash + signature)	No	No	No
Browser-accessible agent identity	Yes (read-only)	No	No	No
URI collision prevention	Domain-anchored	N/A	N/A	N/A
Agent Genesis	Yes (genesis record)	No	No	No
Domain-expiry lifecycle handling	Specified	N/A	N/A	N/A
Capability discovery	Native (DESCRIBE)	None	Reflection (partial)	None
Resource budget enforcement	Specified (Budget-Limit per AGTP-COMMERCE, 456)	None	None	None
Execution attestation (RATS)	Optional (RFC 9334)	None	None	None
Observability hooks	Planned (Telemetry-Export)	None	None	None
Network zone enforcement	Planned (AGTP-Zone-ID, 457)	None	None	None
Session suspension/recovery	Native (SUSPEND method)	None	None	None
AGMP composition profiles	Normative body section	N/A	N/A	N/A

HTTP's method registry is extensible per ; what constrains a new HTTP method is the deployed base that must receive it. AGTP's distinct wire image lets its method vocabulary evolve through the catalog of as the agent ecosystem develops, without the backward-compatibility constraints of the HTTP method space.