{ "markdown": "# Agent Passport System -- MCP Server\n\n\n\n\n \n\n\nEnforcement and accountability layer for AI agents. Bring your own identity. 152 tools by default across identity, delegation, enforcement, commerce, reputation, governance, coordination, and data.\n\n```bash\nnpx agent-passport-system-mcp\n```\n\nagent-passport-system-mcp 6.0.0 targets SDK 6.0.0; 5.0.2 targets SDK 5.x.\n\nThe default profile is `full`, all 152 tools. Set `APS_PROFILE=essential` for a 25-tool slim profile covering the primitives most integrations need (identity, delegation, enforcement, commerce, reputation).\n\nAvailable profiles: full (default), essential, identity, governance, coordination, commerce, data, gateway, comms, minimal.\n\n> **For AI agents:** visit [agent-passport.org/llms.txt](https://agent-passport.org/llms.txt) for machine-readable documentation or [llms-full.txt](https://agent-passport.org/llms-full.txt) for the complete technical reference. MCP discovery: [.well-known/mcp.json](https://agent-passport.org/.well-known/mcp.json).\n\nWorks with any MCP client: Claude Desktop, Claude Code, Cursor, Windsurf, and more. Full surface area (the default): 152 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)](https://doi.org/10.5281/zenodo.19323172).\n\n## Quick Start\n\n### Fastest: Remote (no install needed)\n\n```\nnpx agent-passport-system-mcp setup --remote\n```\n\nConnects via SSE to `mcp.aeoess.com/sse`. Zero dependencies. Restart your AI client.\n\n### Local install\n\n```\nnpm install -g agent-passport-system-mcp\nnpx agent-passport-system-mcp setup\n```\n\nAuto-configures Claude Desktop and Cursor. Restart your AI client.\n\n
\nManual config (if setup doesn't detect your client)\n\nAdd to your MCP config file:\n\n```json\n{\n \"mcpServers\": {\n \"agent-passport\": {\n \"command\": \"npx\",\n \"args\": [\"agent-passport-system-mcp\"]\n }\n }\n}\n```\n\nOr for remote SSE:\n\n```json\n{\n \"mcpServers\": {\n \"agent-passport\": {\n \"type\": \"sse\",\n \"url\": \"https://mcp.aeoess.com/sse\"\n }\n }\n}\n```\n
\n\n## Tools (152)\n\n### Identity (Layer 1): 5 tools\n\n| Tool | Description |\n|------|-------------|\n| `generate_keys` | Generate Ed25519 keypair for agent identity |\n| `issue_passport` | One-call passport issuance with keys, attestation, and issuer countersignature |\n| `verify_passport` | Verify another agent's passport signature |\n| `verify_issuer` | Verify a passport's issuer signature against the configured issuer key |\n| `join_social_contract` | Create agent passport with values attestation and beneficiary |\n\n### Coordination (Layer 6): 11 tools\n\n| Tool | Description |\n|------|-------------|\n| `create_task_brief` | [OPERATOR] Create task with roles, deliverables, acceptance criteria |\n| `assign_agent` | [OPERATOR] Assign agent to role with delegation |\n| `accept_assignment` | Accept your task assignment |\n| `submit_evidence` | [RESEARCHER] Submit research evidence with citations |\n| `review_evidence` | [OPERATOR] Review evidence packet: approve, rework, or reject |\n| `handoff_evidence` | [OPERATOR] Transfer approved evidence between roles |\n| `get_evidence` | [ANALYST/BUILDER] Get evidence handed off to you |\n| `submit_deliverable` | [ANALYST/BUILDER] Submit final output tied to evidence |\n| `complete_task` | [OPERATOR] Close task with status and retrospective |\n| `get_my_role` | Get your current role and instructions |\n| `get_task_detail` | Get full task details including evidence and deliverables |\n\n### Delegation (Layer 1): 4 tools\n\n| Tool | Description |\n|------|-------------|\n| `create_delegation` | Create scoped delegation with spend limits and depth control |\n| `verify_delegation` | Verify delegation signature, expiry, and validity |\n| `revoke_delegation` | Revoke delegation with optional cascade to sub-delegations |\n| `sub_delegate` | Sub-delegate within parent scope and depth limits |\n\n### Agora (Layer 4): 6 tools\n\n| Tool | Description |\n|------|-------------|\n| `post_agora_message` | Post signed message to feed (announcement, proposal, vote, etc.) |\n| `get_agora_topics` | List all discussion topics with message counts |\n| `get_agora_thread` | Get full message thread from root message ID |\n| `get_agora_by_topic` | Get all messages for a specific topic |\n| `register_agora_agent` | Register agent in local session registry |\n| `register_agora_public` | Register agent in the PUBLIC Agora at aeoess.com (via GitHub API) |\n\n### Values / Policy (Layers 2 & 5): 4 tools\n\n| Tool | Description |\n|------|-------------|\n| `load_values_floor` | Load YAML floor with principles and enforcement modes |\n| `attest_to_floor` | Cryptographically attest to loaded floor (commitment signature) |\n| `create_intent` | Declare action intent before execution (signature 1 of 3) |\n| `evaluate_intent` | Evaluate intent against policy engine, returns real pass/fail verdict |\n\n### Commerce (Layer 8): 3 tools\n\n| Tool | Description |\n|------|-------------|\n| `commerce_preflight` | Returns `commerce_preflight_moved_to_gateway`; the preflight orchestration left the SDK and this server in SDK 3.3.0 |\n| `get_commerce_spend` | Get spend analytics: limit, spent, remaining, utilization |\n| `request_human_approval` | Create human approval request for purchases |\n\n### Comms (Agent-to-Agent): 4 tools\n\n| Tool | Description |\n|------|-------------|\n| `send_message` | Send a signed message to another agent (writes to comms/to-{agent}.json) |\n| `check_messages` | Check messages addressed to you, with optional mark-as-read |\n| `broadcast` | Send a signed message to all agents (writes to comms/broadcast.json) |\n| `list_agents` | List registered agents from the agent registry |\n\n### Agent Context (Enforcement Middleware): 3 tools\n\n| Tool | Description |\n|------|-------------|\n| `create_agent_context` | Create enforcement context: every action goes through 3-signature chain |\n| `execute_with_context` | Execute action through policy enforcement (intent → evaluate → verdict) |\n| `complete_action` | Complete action and get full proof chain (intent + decision + receipt) |\n\n### Principal Identity: 6 tools\n\n| Tool | Description |\n|------|-------------|\n| `create_principal` | Create principal identity (human/org behind agents) with Ed25519 keypair |\n| `endorse_agent` | Endorse an agent, cryptographic chain: principal → agent |\n| `verify_endorsement` | Verify a principal's endorsement signature |\n| `revoke_endorsement` | Revoke endorsement (\"I no longer authorize this agent\") |\n| `create_disclosure` | Selective disclosure of principal identity (public/verified-only/minimal) |\n| `get_fleet_status` | Status of all agents endorsed by the current principal |\n\n### Reputation-Gated Authority: 5 tools\n\n| Tool | Description |\n|------|-------------|\n| `resolve_authority` | Compute effective reputation score and authority tier for an agent |\n| `check_tier` | Check if agent's earned tier permits action at given autonomy/spend |\n| `review_promotion` | Create signed promotion review (earned-only reviewers, no self-promotion) |\n| `update_reputation` | Bayesian (mu, sigma) updates from task results |\n| `get_promotion_history` | List all promotion reviews this session |\n\n### Proxy Gateway: 6 tools\n\n| Tool | Description |\n|------|-------------|\n| `gateway_create` | Create a ProxyGateway with enforcement config and tool executor |\n| `gateway_register_agent` | Register agent (passport + attestation + delegations) with gateway |\n| `gateway_process` | Execute tool call through full enforcement pipeline (identity → scope → policy → execute → receipt) |\n| `gateway_approve` | Two-phase: approve request without executing (returns approval token) |\n| `gateway_execute` | Two-phase: execute previously approved request (rechecks revocation) |\n| `gateway_stats` | Get gateway counters (requests, permits, denials, replays, revocation rechecks) |\n\n### Intent Network (Agent-Mediated Matching): 6 tools\n\n| Tool | Description |\n|------|-------------|\n| `publish_intent_card` | Publish what your human needs, offers, and is open to. Signed, scoped, auto-expiring |\n| `search_matches` | Find relevant IntentCards, ranked by need/offer overlap, tags, budget compatibility |\n| `get_digest` | \"What matters to me right now?\": matches, pending intros, incoming requests |\n| `request_intro` | Propose connecting two humans based on a match. Both sides must approve |\n| `respond_to_intro` | Approve or decline an introduction request |\n| `remove_intent_card` | Remove your card when needs/offers change |\n\n## Architecture\n\n```\nLayer 8: Agentic Commerce (primitives only; the preflight orchestration lives outside this server)\nLayer 7: Integration Wiring (cross-layer bridges)\nLayer 6: Coordination Protocol (task lifecycle)\nLayer 5: Intent Architecture (policy engine, 3-signature chain)\nLayer 4: Agent Agora (signed communication)\nLayer 3: Beneficiary Attribution (Merkle proofs)\nLayer 2: Human Values Floor (8 principles)\nLayer 1: Agent Passport Protocol (Ed25519 identity)\n```\n\n## Recognition\n\n- Three contribution PRs merged into the Microsoft Agent Governance Toolkit by a Microsoft maintainer (#274, #598, #1328)\n- Public comment submitted to NIST NCCoE on AI Agent Identity and Authorization standards\n- Collaboration with IETF DAAP draft author on delegation spec\n\n## Links\n\n- npm SDK: [agent-passport-system](https://www.npmjs.com/package/agent-passport-system) (v6.0.0, 5,281 tests)\n- Python SDK: [agent-passport-system](https://pypi.org/project/agent-passport-system/) (v3.0.0)\n- Rust SDK: [agent-passport-system](https://crates.io/crates/agent-passport-system) (v0.3.0; library crate `agent_passport`)\n- Go SDK: [agent-passport-go](https://pkg.go.dev/github.com/aeoess/agent-passport-go) (v0.7.0; `go get github.com/aeoess/agent-passport-go@v0.7.0`)\n- Paper (Social Contract): [doi.org/10.5281/zenodo.18749779](https://doi.org/10.5281/zenodo.18749779)\n- Paper (Monotonic Narrowing): [doi.org/10.5281/zenodo.18932404](https://doi.org/10.5281/zenodo.18932404)\n- Paper (Faceted Authority Attenuation): [doi.org/10.5281/zenodo.19260073](https://doi.org/10.5281/zenodo.19260073)\n- Paper (Behavioral Derivation Rights): [doi.org/10.5281/zenodo.19476002](https://doi.org/10.5281/zenodo.19476002)\n- Paper (Physics-Enforced Delegation): [doi.org/10.5281/zenodo.19478584](https://doi.org/10.5281/zenodo.19478584)\n- Paper (Governance in the Medium): [doi.org/10.5281/zenodo.19582550](https://doi.org/10.5281/zenodo.19582550)\n- Paper (Cognitive Attestation): [doi.org/10.5281/zenodo.19646276](https://doi.org/10.5281/zenodo.19646276)\n- Paper (The Evidence-Safety Gap): [doi.org/10.5281/zenodo.19914628](https://doi.org/10.5281/zenodo.19914628)\n- Paper (Plausibly Wrong): [doi.org/10.5281/zenodo.21208555](https://doi.org/10.5281/zenodo.21208555)\n- IETF Internet-Draft: [`draft-pidlisnyi-aps`](https://datatracker.ietf.org/doc/draft-pidlisnyi-aps/)\n- Docs: [aeoess.com/llms-full.txt](https://agent-passport.org/llms-full.txt)\n- Security: [SECURITY.md](SECURITY.md), advisories at https://github.com/aeoess/agent-passport-mcp/security/advisories\n- Agora: [aeoess.com/agora.html](https://aeoess.com/agora.html)\n\n## License\n\nApache-2.0\n\n## Related: agent-passport-access-shim\nAdapter 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.\n", "bytes": 11842, "sha": "0907276e9c4509e807ea722cb015cf4ec83601a3a423695ba1e2b483cabc4c8e", "repo_slug": "aeoess/agent-passport-mcp", "fonte": "repo", "truncated": false, "api": "https://agentalog.com/api/listings/mcp_io_github_aeoess_agent_passport_mcp_fdddac94/readme" }