AI代理身份与治理MCP服务器

Agent Passport System 是一个为AI代理提供身份认证、权限委托、执行治理与问责能力的MCP服务器,适用于构建需强制安全策略与行为审计的多代理协作系统。

  • by agent-passport-system
  • TypeScript
  • 混合部署
  • 4 星标
  • 更新于
在 GitHub 查看 aeoess/agent-passport-mcp

使用说明

Agent Passport System -- MCP Server

Enforcement and accountability layer for AI agents. Bring your own identity. 154 tools by default across identity, delegation, enforcement, commerce, reputation, governance, coordination, and data.

npx agent-passport-system-mcp

agent-passport-system-mcp 8.1.0, 8.0.0 and 7.0.0 target SDK 8.x. The 6.x line targets SDK 6.x, and 5.0.2 targets SDK 5.x.

The default profile is full, all 154 tools. Set APS_PROFILE=essential for a 28-tool slim profile covering the primitives most integrations need (identity, delegation, enforcement, commerce, reputation). The count is what tools/list returns and includes list_profiles, which every profile exposes.

Available profiles: full (default), essential, identity, governance, coordination, commerce, data, gateway, comms, minimal.

For AI agents: visit agent-passport.org/llms.txt for machine-readable documentation or llms-full.txt for the complete technical reference. MCP discovery: .well-known/mcp.json.

Works with any MCP client: Claude Desktop, Claude Code, Cursor, Windsurf, and more. Full surface area (the default): 154 tools across the protocol surface, including Wave 1 accountability primitives (Ed25519 ActionReceipt, AuthorityBoundaryReceipt, CustodyReceipt, ContestabilityReceipt, APSBundle, strict RFC 8785 JCS for interop-facing receipts, byte-match across implementations). Independently cited by PDR in Production preprint (Nanook & Gerundium).

Quick Start

Fastest: Remote (no install needed)

npx agent-passport-system-mcp setup --remote

Connects via SSE to mcp.aeoess.com/sse. Zero dependencies. Restart your AI client.

Local install

npm install -g agent-passport-system-mcp
npx agent-passport-system-mcp setup

Auto-configures Claude Desktop and Cursor. Restart your AI client.

Manual config (if setup doesn't detect your client)

Add to your MCP config file:

{
  "mcpServers": {
    "agent-passport": {
      "command": "npx",
      "args": ["agent-passport-system-mcp"]
    }
  }
}

Or for remote SSE:

{
  "mcpServers": {
    "agent-passport": {
      "type": "sse",
      "url": "https://mcp.aeoess.com/sse"
    }
  }
}

Tools (154)

Every tool carries MCP annotations. Read-only means the tool writes no file, calls no mutating remote endpoint and changes no session state other tools read. Destructive means it deletes, revokes, supersedes, overwrites or irreversibly consumes something. Network means it can contact an external host (see Network and local files). The hint values live in src/toolAnnotations.ts.

Meta: 2 tools

Tool Title Read-only Destructive Network Description
list_profiles List Tool Profiles yes Show available tool profiles.
list_tools_for_scope List Tools for Delegation Scope yes List available MCP tools filtered by delegation scope.

Identity and key rotation: 15 tools

Tool Title Read-only Destructive Network Description
aps_compute_attribution_action_ref Compute Attribution Action Ref yes Derive the action_ref (hex sha256) for an action tuple.
classify_evidence_quality Classify Evidence Quality yes Classify attestation evidence quality (none / issuer_vouched / infrastructure / principal_bound) and return the corresponding grade (0-3).
compute_action_ref Compute Action Reference yes Compute content-addressed request identity (SHA-256 of agentId + actionType + scope + normalized timestamp).
generate_keys Generate Ed25519 Keypair yes Generate an Ed25519 keypair for agent identity.
get_behavioral_sequence Get Post-Issuance Behavior yes Get the post-issuance behavioral sequence for an agent.
get_my_role Get My Coordination Role yes Get your current role, assigned tasks, and role-specific instructions.
get_passport_grade Get Passport Grade yes Query the attestation grade and issuance context for a passport.
identify Identify Session Agent Identify yourself to the coordination server.
is_evidence_fresh Check Evidence Freshness yes Check whether typed attestation evidence is still fresh.
is_key_active Check Key Is Active yes Check if a public key is currently authorized for active operations in a DID document.
issue_passport Issue Agent Passport yes Issue a complete agent passport with keys, signed passport, attestation summary, and optional values floor in a single call.
list_issuance_records List Issuance Records yes List all stored issuance records with their passport grades.
rotate_key Rotate Agent Key yes Rotate an agent's Ed25519 key.
verify_issuer Verify Passport Issuer Signature yes Verify that a passport was officially issued by AEOESS.
verify_rotation_chain Verify Key Rotation Chain yes Verify all rotation signatures in a DID document's rotation log.

Delegation and escalation: 10 tools

Tool Title Read-only Destructive Network Description
aps_check_escalation_required Check Escalation Required yes Escalation boundary: check whether an action on a v2 delegation requires owner confirmation before execution.
aps_record_owner_confirmation Record Owner Confirmation yes Escalation boundary: owner signs an OwnerConfirmation authorizing a flagged action.
check_authority_delegation Check Authority Delegation yes Verify a root AuthorityDelegationV1 issued by this server's key, with the SDK chain verifier: shape, delegation_id, signature, time window and revocation status from this proces...
create_delegation Create Delegation [OPERATOR] Create a scoped delegation from one agent to another.
create_v2_delegation Create v2 Delegation Create a v2 delegation with versioning, mandatory sunset, and PolicyContext binding.
issue_authority_delegation Issue Authority Delegation [OPERATOR] Issue a signed root AuthorityDelegationV1 (record_type aps:authority-delegation:v1, draft-03 section 3.1) from this server's key to a subject.
revoke_delegation Revoke Delegation yes [OPERATOR] Issue a signed revocation record (AuthorityRevocationV1, draft-03 section 3.5.1 direct revocation) for an AuthorityDelegationV1.
sub_delegate Sub-Delegate Authority Sub-delegate authority to another agent (must be within your delegation scope and depth).
supersede_v2_delegation Supersede v2 Delegation yes Supersede a v2 delegation.
verify_delegation Verify Delegation yes Check a delegation's signature and its stated window.

Principal identity: 6 tools

Tool Title Read-only Destructive Network Description
create_disclosure Create Principal Disclosure yes Create a selective disclosure of principal identity.
create_principal Create Principal Identity yes Create a principal identity (human or org behind agents) with its own Ed25519 keypair, held in this process as the session principal with a new fleet.
endorse_agent Endorse Agent Endorse an agent as a principal.
get_fleet_status Get Fleet Status yes Get status of all agents endorsed by the current principal.
revoke_endorsement Revoke Endorsement yes Revoke a principal's endorsement of an agent.
verify_endorsement Verify Endorsement yes Check an endorsement's signature against the principalPublicKey the endorsement itself carries.

Reputation-gated authority: 7 tools

Tool Title Read-only Destructive Network Description
apply_reputation_downgrade Apply Reputation Downgrade yes Apply import policy downgrade to a foreign vouched reputation.
check_tier Check Tier Permits Action yes Check if an agent's earned tier permits an action at a given autonomy level and spend amount.
get_promotion_history Get Promotion History yes Get the promotion review history for this session.
resolve_authority Resolve Authority Tier yes Compute effective reputation score and authority tier for an agent in a given scope.
review_promotion Review Agent Promotion (Unavailable) yes Unavailable with SDK 8.
update_reputation Update Agent Reputation Update an agent's reputation after a task result.
vouch_reputation Vouch Reputation yes Create a signed reputation summary that another gateway can import.

Coordination and provisional statements: 15 tools

Tool Title Read-only Destructive Network Description
accept_assignment Accept Task Assignment [ANY ROLE] Accept your task assignment.
aps_create_provisional Create Provisional Statement yes Commitment boundary: emit a provisional statement for agent-to-agent negotiation.
aps_promote_statement Promote Provisional Statement yes Commitment boundary: promote a provisional statement to binding by attaching a PromotionEvent that satisfies the PromotionPolicy (m-of-n principal signatures).
aps_verify_promotion Verify Statement Promotion yes Commitment boundary: verify that a promoted statement's PromotionEvent cryptographically satisfies the PromotionPolicy (policy_reference match, promoter in required_signers, thr...
aps_withdraw_provisional Withdraw Provisional Statement yes Commitment boundary: author withdraws their own provisional statement.
assign_agent Assign Agent to Task Role [OPERATOR] Assign an agent to a role in a task.
complete_task Complete Task yes [OPERATOR] Close the task unit with final status and retrospective.
create_task_brief Create Task Brief [OPERATOR] Create a new task with roles, deliverables, and acceptance criteria.
get_evidence Get Handed-Off Evidence yes [ANALYST/BUILDER/REVIEWER] Get evidence that was handed off to you.
get_task_detail Get Task Detail yes Get full details of a specific task including all evidence, reviews, and deliverables.
handoff_evidence Hand Off Evidence [OPERATOR] Transfer approved evidence from researcher to analyst.
list_tasks List Tasks yes List all tasks in the coordination store.
review_evidence Review Evidence Packet [OPERATOR] Review an evidence packet.
submit_deliverable Submit Deliverable [ANALYST/BUILDER] Submit your final output tied to evidence.
submit_evidence Submit Evidence Packet [RESEARCHER] Submit research evidence as a signed packet with citations.

Agora and agent messaging: 10 tools

Tool Title Read-only Destructive Network Description
broadcast Broadcast Agent Message Send a signed message to all agents via comms/broadcast.json.
check_messages Check Agent Messages Check messages addressed to you.
get_agora_by_topic Get Agora Messages by Topic yes Get all messages in a topic.
get_agora_thread Get Agora Thread yes Get a message thread from the Agora feed.
get_agora_topics List Agora Topics yes List all topics in the Agora feed with message counts.
list_agents List Registered Agents yes List registered agents from the agent registry (agora/agents.json).
post_agora_message Post Agora Message Post a signed message to the Agora feed.
register_agora_agent Register Agent in Session Agora Register an agent in the Agora so their messages can be verified.
register_agora_public Register Agent in Public Agora yes Register your agent in the PUBLIC Agora registry at aeoess.com.
send_message Send Agent Message Send a signed message to another agent.

Governance, charters, provenance, attribution: 40 tools

Tool Title Read-only Destructive Network Description
activate_emergency Activate Emergency Pathway Activate a pre-authorized emergency pathway with evidence.
add_approval_signature Add Approval Signature Add a signature to an approval request.
add_principal_report Add Principal Outcome Report Add principal's perspective to an outcome record.
aps_attribution_receipt_id Compute Attribution Receipt ID yes Representation boundary helper: compute the canonical sha256 id of an AttributionReceipt's unsigned core.
aps_check_artifact_citations Check Artifact Citations yes Representation boundary: gate a binding artifact's citations.
aps_check_projection_consistency Check Projection Consistency yes Cross-projection consistency check: given two projections, confirm they originate from the same signed receipt.
aps_construct_attribution_primitive Construct Attribution Primitive yes Build and sign a four-axis AttributionPrimitive for an action.
aps_create_attribution_receipt Create Attribution Receipt yes Representation boundary: build a citer-signed AttributionReceipt attributing a claim to a third-party principal.
aps_project_attribution Project Attribution Axis yes Extract a single-axis projection from an AttributionPrimitive.
aps_sign_attribution_consent Sign Attribution Consent yes Representation boundary: the cited principal adds their consent signature to an AttributionReceipt.
aps_verify_attribution_consent Verify Attribution Consent yes Representation boundary: verify an AttributionReceipt end-to-end (id, citer signature, consent signature, expiry) and bind each named party to the key beside it.
aps_verify_attribution_primitive Verify Attribution Primitive yes End-to-end verify of a full AttributionPrimitive: constructs projections for all four axes and verifies each one.
aps_verify_attribution_projection Verify Attribution Projection yes Verify a single-axis AttributionProjection under the issuer's Ed25519 public key.
attest_to_floor Attest to Values Floor yes Attest that your agent agrees to abide by the loaded Values Floor.
complete_action Complete Action (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Complete a permitted action and get the full 3-signature proof chain.
compute_governance_taint Compute Governance Taint yes Compute governance taint level for an artifact based on its derivation chain and revoked sources.
create_agent_context Create Agent Context (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Create an enforcement context that automatically runs every action through the 3-signature policy chain.
create_approval_request Create Approval Request Create a multi-party approval request for charter amendments, office transfers, etc.
create_artifact_provenance Create Artifact Provenance yes Tag an agent-generated artifact with provenance metadata (content hash, risk class, authoring agent).
create_chained_governance_block Create Chained Governance Block yes Create a governance block for derivative content that references the original publisher's block.
create_charter Create Charter Create a new institutional charter, the constitutional root of an organization.
create_intent Create Action Intent Declare an intent to perform an action.
create_outcome_record Create Outcome Record Register an action outcome (agent perspective).
create_policy_context Create Policy Context yes Create a v2 PolicyContext with mandatory sunset.
define_emergency_pathway Define Emergency Pathway Define a pre-authorized emergency pathway at delegation time.
evaluate_intent Evaluate Action Intent yes [OPERATOR] Evaluate an intent against the Values Floor policy engine.
execute_with_context Execute with Context (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Execute an action through the enforcement context.
generate_aps_txt Generate aps.txt yes Generate a signed aps.txt file for site-wide governance.
generate_governance_block Generate Governance Block yes Generate a cryptographically signed governance block for embedding in HTML pages.
governance_360 Run Governance 360 Loop yes Execute the full governance 360 loop on HTML content: extract governance block → verify signature + content hash → check usage terms → create signed access receipt.
load_values_floor Load Values Floor Load a Values Floor from YAML.
parse_governance_block_html Parse Governance Block from HTML yes Extract a governance block from an HTML page.
propose_amendment Propose Charter Amendment Propose an amendment to a charter.
resolve_path_terms Resolve Path Terms yes Resolve governance terms for a specific URL path using aps.txt path overrides.
sign_amendment Sign Charter Amendment Add a signature to a proposed amendment.
sign_charter Sign Charter Add a founding signature to a charter.
verify_amendment Verify Charter Amendment yes Verify an amendment against its charter's amendment policy.
verify_aps_txt Verify aps.txt yes Verify a signed aps.txt file by checking its signature and DID consistency.
verify_charter Verify Charter yes Verify a charter's integrity: content hash, signatures, quorum, dissolution, office consistency, incompatibility, and, when the charter declares citations, the AttributionConsen...
verify_governance_block Verify Governance Block yes Verify a governance block's signature, content hash, DID consistency and expiry against the original content.

Commerce: 3 tools

Tool Title Read-only Destructive Network Description
commerce_preflight Commerce Preflight (Moved to Gateway) yes [moved to gateway in SDK 3.3.0] The 6-gate commerce preflight orchestration moved out of the SDK and MCP into the AEOESS gateway.
get_commerce_spend Get Commerce Spend yes Get spend analytics for a commerce delegation.
request_human_approval Build Human Approval Request yes Create an approval request record for a high-value purchase without notifying a human or storing the request.

Data governance: 20 tools

Tool Title Read-only Destructive Network Description
check_aggregate_constraints Check Aggregate Constraints yes Check if a data access would violate aggregate rate limits.
check_combination_permitted Check Data Combination Permitted yes Check if combining data from two sources is permitted.
check_jurisdiction_transfer Check Jurisdiction Transfer yes Check if a data transfer is permitted under jurisdiction constraints (EU_ONLY, GDPR_ADEQUATE_ONLY, NO_CROSS_BORDER).
check_purpose_permitted Check Purpose Permitted yes Check if a purpose is permitted under source terms.
check_retention_expired Check Retention Expired yes Check if data retention has expired based on TTL policy.
check_usage_permitted Check Usage Permitted yes Check if a specific usage type is permitted under a governance block's terms.
create_access_receipt Create Access Receipt yes Create a signed receipt recording the supplied content reference and terms, after verifying the governance block against the content and the publisher's key.
create_access_snapshot Create Access Snapshot yes Create a signed access snapshot that pins terms, jurisdiction, and constraints at the moment of access, so a later change to the source terms does not alter what the snapshot re...
create_data_enforcement_gate Create Data Enforcement Gate (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Create a data enforcement gate that checks terms before allowing data access.
create_decision_lineage_receipt Create Decision Lineage Receipt yes Create a Decision Lineage Receipt that traces which data sources influenced a decision.
create_derivation_receipt Create Derivation Receipt yes Create a signed derivation receipt tracking how data was transformed.
declare_reidentification_risk Declare Re-identification Risk yes Declare re-identification risk for transformed or synthetic data.
detect_purpose_drift Detect Purpose Drift yes Detect when data purpose drifts through a workflow (e.g. research → commercial).
evaluate_revocation_impact Evaluate Revocation Impact yes Evaluate what happens when a data source revokes consent.
file_data_dispute Build Data Dispute Record yes Create a signed dispute record against a data artifact without submitting, storing, or sending it.
generate_settlement Generate Settlement (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Generate a Merkle-committed, signed settlement record for a period.
query_contributions Query Contributions (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Query the data contribution ledger.
register_data_source Register Data Source Register a data source with terms for agent access.
resolve_lineage Resolve Data Lineage yes Resolve the full derivation chain for an artifact.
resolve_rights_propagation Resolve Rights Propagation yes Resolve what rights propagate when data is transformed.

Gateway (removed in v3.0.0, stubs return a migration notice): 4 tools

Tool Title Read-only Destructive Network Description
create_gateway Create Gateway (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Create a ProxyGateway enforcement boundary.
gateway_approve Gateway Approve (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Two-phase execution: approve a tool call without executing it.
gateway_process_tool_call Gateway Process Tool Call (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Process a tool call through the gateway enforcement boundary.
gateway_stats Gateway Stats (Deprecated) yes [deprecated in v3.0.0, use the gateway.aeoess.com REST API] Get gateway statistics.

Intent Network: 5 tools

Tool Title Read-only Destructive Network Description
get_digest Get Intent Network Digest yes yes Get a personalized digest from the Intent Network: relevant matches, pending intro requests, and incoming intros.
remove_intent_card Remove Intent Card yes yes Remove your IntentCard from the Intent Network.
request_intro Request Introduction yes Request an introduction to another agent's human based on a match.
respond_to_intro Respond to Introduction yes yes Respond to an introduction request.
search_matches Search Intent Network Matches yes yes Search the Intent Network for people relevant to you.

Time and reserve attestation: 4 tools

Tool Title Read-only Destructive Network Description
compare_timestamps Compare Hybrid Timestamps yes Compare two hybrid timestamps to determine ordering.
create_hybrid_timestamp Create Hybrid Timestamp yes Create a hybrid timestamp using the local clock and a supplied uncertainty bound.
create_reserve_attestation Create Reserve Attestation yes Sign a reserve attestation using the supplied amount and assurance class.
validate_temporal_rights Validate Temporal Rights yes Validate a TemporalRights object by checking its validity window, grace period, supersession, and challenge window.

Attribution weights: 2 tools

Tool Title Read-only Destructive Network Description
aps_compute_compute_axis_weights Compute Compute Axis Weights yes Compute the C-axis fractional weight vector from a list of inference billing records (prompt_tokens, completion_tokens).
aps_compute_data_axis_weights Compute Data Axis Weights yes Compute the D-axis fractional weight vector from a list of AccessReceipt records with role, timestamp, and content length.

Attribution settlement: 3 tools

Tool Title Read-only Destructive Network Description
aps_aggregate_settlement Aggregate Settlement Record yes Aggregate a batch of Attribution Primitives over a half-open settlement period [t0, t1) into a signed SettlementRecord.
aps_build_contributor_query Build Contributor Query Response yes Build a contributor-query response: given a signed SettlementRecord and a contributor DID, return per-axis (total_weight, contribution_count, merkle_path, axis_root) plus the fu...
aps_verify_settlement Verify Settlement Record yes Verify a signed SettlementRecord under S1-S5 (signature, Merkle roots, conservation, residual shape, optional input-receipts cross-check).

Capability token v0.1: 4 tools

Tool Title Read-only Destructive Network Description
aps_capability_evaluate_authority Build Authority Evaluation Request yes v0.1 capability-token authority evaluation request (M2).
aps_capability_issue_challenge Issue Capability Sink Challenge yes v0.1 capability-token sink challenge (M1).
aps_capability_mint_receipt Mint Capability Challenge Receipt yes v0.1 capability-token gateway receipt (M3).
aps_capability_sign_effect Sign Capability Effect Receipt yes v0.1 capability-token sink effect receipt (M4).

Mutual authentication: 4 tools

Tool Title Read-only Destructive Network Description
mutualAuthBuildCertificate Build Mutual-Auth Certificate yes Build and sign a mutual-auth certificate identifying an agent or information system.
mutualAuthDeriveSession Derive Mutual-Auth Session yes Derive the shared mutual-auth session record from both sides' Attests.
mutualAuthVerifyAttest Verify Mutual-Auth Attest yes Verify a MutualAuthAttest against policy and trust anchors.
mutualAuthVerifyTrustBundle Verify Trust Anchor Bundle yes Verify a TrustAnchorBundle signature and freshness.

Network and local files

The server makes outbound requests only from the tools below. Every other tool works offline. The Network column in the tables above marks the same set.

Host Tools What is sent
api.aeoess.com (override with INTENT_API_URL) search_matches, get_digest (GET), request_intro (POST), respond_to_intro (PUT), remove_intent_card (DELETE) The session agent ID and public key as X-Agent-Id and X-Public-Key headers, plus the tool arguments and a signature where the tool signs
api.github.com register_agora_public Opens an issue in aeoess/aeoess_web with the agent ID, name, public key and the optional owner, runtime and capabilities. The token comes from the token argument, or from the GITHUB_TOKEN environment variable when the argument is absent. With no token the tool makes no request and returns a github.com URL to open by hand
AEOESS_GATEWAY_URL (for example gateway.aeoess.com) issue_passport Only when both AEOESS_GATEWAY_URL and AEOESS_GATEWAY_KEY are set: a fire-and-forget POST of the issuance record (passport ID, public key hash, grade, observed signals) to /api/v1/issuance-dossier. Off by default

gateway.aeoess.com and aeoess.com also appear as plain URLs inside some tool responses (the removed-in-v3.0.0 stubs and the latest.json the Agora writes). The server does not fetch them. npx agent-passport-system-mcp setup --remote writes https://mcp.aeoess.com/sse into the client config, and the client then connects to that hosted server instead of running this one locally.

Local files the server reads or writes, all under the user's home directory unless overridden:

Path Tools Access
~/.agent-passport-tasks.json coordination tools (create_task_brief, assign_agent, accept_assignment, submit_evidence, review_evidence, handoff_evidence, submit_deliverable, complete_task) read at startup, written by those tools
AGORA_PATH, default ~/aeoess_web/agora/messages.json and latest.json beside it post_agora_message read at startup, written on post
AGENTS_PATH, default ~/aeoess_web/agora/agents.json list_agents read
COMMS_PATH, default ~/aeoess_web/comms/ send_message, broadcast, check_messages (writes only with mark_read) read and written
APS_NULLIFIER_DIR, default ~/.agent-passport-nullifiers/ aps_capability_sign_effect SHA-256 hashes identifying consumed tokens, with redemption timestamps. Raw preimages are not stored. Written on redemption
Claude Desktop and Cursor MCP config files the setup command, not a tool adds the agent-passport server entry

Keys are never written to disk by the server. identify holds the agent key pair in process memory for the session, and AGENT_KEY / AGENT_PRIVATE_KEY supply it from the environment. generate_keys, issue_passport and rotate_key return private keys in the tool response, and generate_keys and issue_passport redact them when the server runs in remote mode. create_principal keeps the principal key in memory and returns the full private key once on a local (stdio) server, redacted in remote mode as in generate_keys. It refuses to replace an existing principal unless called with replace=true. Many signing tools take a private key as an argument and use it for that call only. Session state (delegations, endorsements, charters, intents) lives in memory and is lost on restart.

Architecture

Layer 8: Agentic Commerce (primitives only; the preflight orchestration lives outside this server)
Layer 7: Integration Wiring (cross-layer bridges)
Layer 6: Coordination Protocol (task lifecycle)
Layer 5: Intent Architecture (policy engine, 3-signature chain)
Layer 4: Agent Agora (signed communication)
Layer 3: Beneficiary Attribution (Merkle proofs)
Layer 2: Human Values Floor (8 principles)
Layer 1: Agent Passport Protocol (Ed25519 identity)

Recognition

  • Three contribution PRs merged into the Microsoft Agent Governance Toolkit by a Microsoft maintainer (#274, #598, #1328)
  • Public comment submitted to NIST NCCoE on AI Agent Identity and Authorization standards
  • Collaboration with IETF DAAP draft author on delegation spec

Links

License

Apache-2.0

Related: agent-passport-access-shim

Adapter that emits a signed AccessReceipt for each governed MCP tools/call: https://www.npmjs.com/package/agent-passport-access-shim. Receipts verify with the SDK or in the browser at https://agent-passport.org/verify.html.