{"name":"Agent Verification API","description":"Confirms an AI agent/service is who it claims to be: cross-signal domain verification fused with a real agent-card fetch and a real MCP handshake.","url":"https://agent-verification-api-325572559480.us-central1.run.app","version":"1.0.0","documentationUrl":"https://agent-verification-api-325572559480.us-central1.run.app/docs","provider":{"organization":"nexus-mcp-infra","url":"https://github.com/nexus-mcp-infra"},"capabilities":{"streaming":false,"pushNotifications":false,"stateTransitionHistory":false},"defaultInputModes":["application/json"],"defaultOutputModes":["application/json"],"additionalInterfaces":[{"url":"https://agent-verification-api-325572559480.us-central1.run.app/mcp","transport":"MCP"}],"skills":[{"id":"nexus_agent_verification_api_verify_agent_identity","name":"Verify Agent Identity","description":"Confirm an AI agent/service is who it claims to be, fusing domain existence verification with agent-card and MCP-handshake evidence.","tags":["agent-identity","verification","anti-hallucination","trust"]}],"metadata":{"protocol_note":"This service implements the Model Context Protocol (MCP) at /mcp, not A2A's own task methods. POST /verify-agent-identity is charged $0.35 via x402 (Base Sepolia TESTNET, not real funds) -- higher than a simple metadata-extraction call because each request does real paid WHOIS spend plus 5-6 real outbound checks (WHOIS, Certificate Transparency, Wayback Machine, DNS, agent-card fetch, MCP handshake), not one. The MCP tool is currently free -- see README. Payment settles BEFORE verification runs, at the ASGI middleware layer ahead of request validation: a call is charged even if it returns a non-VERIFIED verdict, and even if it 400s (invalid domain / agent_endpoint_url rejected by the SSRF guard) or 422s (malformed body)."}}