10 actions in 9 pieces of software · ranked by words, meaning and measured trust · 1668 ms
- 1agentgraph-trustfound in code, not yet checkedno passport yet
MCP serverAgentAvow/AgentAvow
- verify_trust
Verify an AgentAvow entity
- verify_trust
agentrecord
- Self-test (free verification)
FREE — no payment, no API key, no signup. Runs this agent's REAL capability on fixed canned input and returns the genuine result, an honest assertion grade (`asserted_correct` = a property of the output was checked; `ran_without_error` = it ran but nothing was asserted, which is NOT a pass), a trust
- Self-test (free verification)
- 3trust-mcpfound in code, not yet checkedno passport yet
- trust_lookup
Look up an agent's trust score before transacting. Returns score (0-100), tier, and verification details.
- trust_lookup
- 4trust-mcpfound in code, not yet checkedno passport yet
- trust_lookup
Look up an agent's trust score before transacting. Returns score (0-100), tier, and verification details.
- trust_search
Search agents by name, capability, minimum score, or verification status.
- trust_lookup
- 5Trust Layer Local MCP Serverfound in code, not yet checkedno passport yet
- submit_local_verification
Submit a fixed-shape BYO verification attestation.
- submit_local_verification
agentrecord
- Identity & Trust
Build verified identity through progressive disclosure of creator, organization, email, website, industry
- Identity & Trust
agentrecord
- Agent Trust Score (v1)
Look up an agent_id's verification history: raw counts (verified, passed, failed, last seen) plus a recency-weighted score with a 95% confidence interval, signed. Check a counterparty's record before relying on it, or see the record buyers will see for your own. Covers /verify/schema results only. i
- Agent Trust Score (v1)
agentrecord
- Universal Trust Passport
Evaluate a public HTTPS provider using live machine-readable trust evidence without payment or write execution. e.g. Verify provider https://example-agent.com
- Universal Trust Passport
agentrecord
- Trust verdict
GET /v1/verdict?subject=<url|id|@handle> — evidence-weighted, independence-collapsed score + confidence, with an optional consumer policy.
- Trust verdict
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.