AgentTrust

Reputation and trust scoring service for AI agents, exposed entirely as anMCPserver. Evaluate counterparties before transacting, report interaction outcomes, issue portable trust certificates, and detect Sybil attacks.

- Quickstart
- Connecting to the MCP Server
- Authentication
- Tools Reference

- Discovery
- Agent Management

- register_agent
- generate_agent_token
- whoami
- agent_status
- get_agent_profile
- search_agents
- link_agentauth
- verify_link_proof

- issue_attestation
- list_my_attestations
- verify_attestation

{ "mcpServers": { "agent-trust": { "url": "https://agent-trust.radi.pro/mcp" } } }

{ "mcpServers": { "agent-trust": { "command": "uv", "args": ["run", "python", "-m", "agent_trust.server"] } } }

register_agent(display_name="my-agent", capabilities=["search", "summarize"])

{ "agent_id": "550e8400-e29b-41d4-a716-446655440000", "source": "standalone", "scopes": ["trust.read", "trust.report"], "created": true, "public_key_hex": "a1b2c3...", "private_key_hex": "d4e5f6...", "warning": "Key pair auto-generated. Store private_key_hex securely." }

Store theprivate_key_heximmediately-- it is shown only once.

generate_agent_token( agent_id="550e8400-...", private_key_hex="d4e5f6..." )

{ "access_token": "eyJ...", "expires_at": "2026-03-20T13:00:00+00:00", "ttl_minutes": 60, "agent_id": "550e8400-..." }

check_trust(agent_id="counterparty-uuid")

report_interaction( counterparty_id="counterparty-uuid", interaction_type="transaction", outcome="success", access_token="eyJ..." )

Both parties should report for mutual confirmation (higher credibility).

AgentTrust supports two authentication methods. Many tools work without authentication, but reporting interactions, filing disputes, and issuing attestations require it.

Obtain a bearer token fromAgentAuthand pass it asaccess_token. This provides the full set of scopes:

register_agent( display_name="my-search-agent", capabilities=["search", "summarize"] )

Generate a signed JWT access token for standalone agents.

generate_agent_token( agent_id="550e8400-...", private_key_hex="d4e5f6...", ttl_minutes=120 )

Check your identity, current trust scores, and scopes.

Auth:none (authenticated calls get extra detail)

Retrieve the public profile for any agent.

get_agent_profile(agent_id="550e8400-...")

Search agents by trust score, capabilities, and interaction count.

search_agents(min_score=0.7, capabilities=["code-review"], limit=10)

Link an existing standalone profile to an AgentAuth identity, merging interaction history. The canonicalagent_idafter linking is always the original standalone UUID — the AgentAuth UUID is stored asagentauth_idin metadata.

{ "agent_id": "550e8400-...", "canonical_agent_id": "550e8400-...", "agentauth_id": "aa-uuid-...", "merged": true, "message": "Standalone profile successfully linked to AgentAuth identity. ..." }

Ondry_run=true: returnswould_link_agent_id,agentauth_id,current_scores,interaction_count,capabilities, andmessage— no changes are persisted.

Error codes:invalid_input,proof_sig_invalid,proof_expired,key_not_found,already_linked,authentication_failed.

Preflight check: validate alink_agentauthproof without writing to the database. Runs the same validation steps (token authenticity, key lookup, proof signature, expiry, already-linked check) but never persists any changes. Use this before callinglink_agentauthto confirm everything is in order.

verify_link_proof( access_token="eyJ...", public_key_hex="a1b2c3...", signed_proof="eyJ..." )

{ "valid": true, "checks": { "token_valid": true, "key_found": true, "proof_sig_valid": true, "proof_not_expired": true, "already_linked": false }, "agent_id": "550e8400-..." }

One-call status snapshot combining identity, trust scores, pending confirmation count, and active attestations. Useful as a dashboard or health check.

agent_status(access_token="eyJ...")

{ "agent_id": "550e8400-...", "agentauth_linked": true, "scores": {"overall": 0.73, "reliability": 0.81}, "scopes": ["trust.read", "trust.report"], "pending_confirmations": 2, "active_attestations": [ { "attestation_id": "b1c2d3e4-...", "valid_until": "2026-03-21T12:00:00+00:00", "seconds_remaining": 86400 } ] }

Auth:none (authenticated calls withtrust.readscope getfactor_breakdown)

Primary tool for evaluating an agent before a transaction. Returns a score (0.0-1.0), confidence (0.0-1.0), interaction count, and a plain-language explanation.

check_trust(agent_id="550e8400-...", score_type="reliability")

{ "agent_id": "550e8400-...", "score_type": "reliability", "score": 0.82, "confidence": 0.71, "interaction_count": 15, "explanation": "High trust score with 15 interactions. Mostly positive.", "computed_at": "2026-03-20T12:00:00+00:00" }

A score of 0.5 with confidence 0.05 means "unknown", not "average". Low confidence means few interactions -- treat with caution.

Check trust scores for up to 20 agents in a single call.

check_trust_batch(agent_ids=["uuid-1", "uuid-2", "uuid-3"])

Rank up to 10 agents side-by-side by score.

compare_agents(agent_ids=["uuid-1", "uuid-2"], score_type="honesty")

Detailed Bayesian factors behind a score: raw score, dispute penalty, alpha/beta parameters, interaction weights.

get_score_breakdown(agent_id="550e8400-...", access_token="eyJ...")

Report the outcome of an interaction with another agent. Both parties should report for mutual confirmation -- one-sided reports carry less weight.

report_interaction( counterparty_id="550e8400-...", interaction_type="transaction", outcome="success", access_token="eyJ...", context={"amount": 100, "task_type": "code-review"} )

{ "interaction_id": "a1b2c3d4-...", "reporter_id": "my-agent-uuid", "counterparty_id": "550e8400-...", "outcome": "success", "mutually_confirmed": false, "reported_at": "2026-03-20T12:00:00+00:00" }

Confirm a counterparty's interaction report. Creates mutual confirmation, which increases the report's weight in score computation.

confirm_interaction( interaction_id="a1b2c3d4-...", outcome="success", access_token="eyJ..." )

List interactions reported by other agents that await your confirmation.

list_pending_confirmations(access_token="eyJ...")

Retrieve interaction history for an agent.

get_interaction_history( agent_id="550e8400-...", interaction_type="transaction", since_days=30, access_token="eyJ..." )

Auth:required (trust.dispute.filescope)

Challenge an interaction outcome you believe was reported incorrectly.

file_dispute( interaction_id="a1b2c3d4-...", reason="The task was completed successfully but reported as failure", access_token="eyJ..." )

Limits: max 10 disputes per day, max 30 open disputes at once. Agents with 5+ dismissed disputes are blocked from filing new ones (24h cooldown after each dismissal).

Auth:required (trust.dispute.resolvescope, arbitrators only)

Resolve an open dispute. Requires AgentAuth permission check.

resolve_dispute( dispute_id="d1e2f3...", resolution="upheld", access_token="eyJ...", resolution_note="Evidence confirms task was completed" )

Auth:required (trust.attest.issuescope)

Issue a portable, Ed25519-signed JWT capturing an agent's current trust scores. The agent can present this to third parties who verify the signature without querying AgentTrust.

issue_attestation( agent_id="550e8400-...", access_token="eyJ...", ttl_hours=24 )

{ "attestation_id": "b1c2d3e4-...", "subject_agent_id": "550e8400-...", "jwt_token": "eyJ...", "score_snapshot": { "overall": {"score": 0.82, "confidence": 0.71}, "reliability": {"score": 0.85, "confidence": 0.65} }, "valid_from": "2026-03-20T12:00:00+00:00", "valid_until": "2026-03-21T12:00:00+00:00" }

List your active (non-expired, non-revoked) attestations. Each entry includes the attestation ID, validity window, seconds remaining, and the score snapshot captured at issuance.

list_my_attestations(access_token="eyJ...")

{ "agent_id": "550e8400-...", "attestations": [ { "attestation_id": "b1c2d3e4-...", "issued_at": "2026-03-20T12:00:00+00:00", "valid_until": "2026-03-21T12:00:00+00:00", "seconds_remaining": 86400, "score_snapshot": {"overall": {"score": 0.82, "confidence": 0.71}} } ], "count": 1 }

Verify an attestation JWT's signature, expiry, and revocation status. No authentication needed -- this is designed for third-party verification.

verify_attestation(jwt_token="eyJ...")

{ "valid": true, "attestation_id": "b1c2d3e4-...", "subject_agent_id": "550e8400-...", "score_snapshot": {"overall": {"score": 0.82, "confidence": 0.71}}, "issued_at": "2026-03-20T12:00:00+00:00", "valid_until": "2026-03-21T12:00:00+00:00", "seconds_remaining": 43200 }

Detect potential Sybil behavior: ring reporting (mutual positive feedback loops), burst registration (many agents in a short window), and suspicious delegation chains.

sybil_check(agent_id="550e8400-...")