{"attribution":"MCP Queen — the evidence layer for MCP (https://mcpqueen.com)","license":"CC BY 4.0 — free to use with attribution and a link to mcpqueen.com","methodology":"https://mcpqueen.com/registry#methodology","docs":"https://mcpqueen.com/api","generated_at":"2026-08-28T17:24:35.842Z","server":{"name":"com.wingmanprotocol.agent/gateway","title":"WingmanProtocol Agent Gateway","description":"Durable self for AI agents: one-call resume, memory, real browser, free chat + hire real humans.","version":"1.5.1","remote_url":"https://wingmanprotocol.com/mcp","repo_url":"https://github.com/RIPRODUCTIONS/wingman-agent-gateway"},"operational_grade":{"grade":"A","score":93,"provisional":0,"reachable":1,"auth_state":"open","latency_ms":277,"tool_count":57,"probed_at":"2026-08-27T00:15:35.239Z","evidence":[{"criterion":"reachability","points":25,"max":25,"evidence":"HTTP 200, initialize accepted in 277ms"},{"criterion":"protocol","points":15,"max":15,"evidence":"valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo com.wingmanprotocol.agent/gateway@1.6.0"},{"criterion":"tooling","points":35,"max":35,"evidence":"tools/list OK: 57 tools e.g. \"discover_tools\"; 57/57 described, 56/57 fully-typed schemas, median description 176 chars"},{"criterion":"latency","points":10,"max":10,"evidence":"initialize round-trip 277ms"},{"criterion":"provenance","points":8,"max":15,"evidence":"description present; repository linked; version 1.5.1; namespace com.wingmanprotocol.agent does NOT match remote host (expected *.agent.wingmanprotocol.com)"}],"protocol_access":"open"},"field_semantics":{"auth_state":"Deprecated name retained for compatibility. It means protocol handshake/discovery access only, not tool-level data entitlement.","protocol_access":"Preferred name for auth_state."},"audit_state":"observations_published","observations":[{"dimension":"citation_quality","metric":"citation_capability_advertised","status":"unverified","value_text":null,"evidence":"Metadata/tool descriptions advertise citation or evidence capability: y' (ping a callback in N seconds), or 'deep_research' (multi-round web search → render → refine → a cited markdown report artifact, ~1–2 min; poll check_errand for it, one in flight per agent) | l web research: searches the web, renders the top hits in the real browser, and returns a GROUNDED, CITED answer ({answer, sources:[{n,title,url}]}). No response-level citation benchmark has verified this claim yet.","source_type":"live_probe","sample_size":null,"observed_at":"2026-08-27T00:15:35.239Z","methodology_version":"trust-v1"},{"dimension":"security","metric":"sensitive_capabilities_declared","status":"concern","value_text":"register_agent, create_watch, list_watches, cancel_watch, check_inbox, read_message, send_message, mark_message, archive_message, resume, confirm_delivery, set_focus, resolve_focus, request_handoff, read_memory_changes, summarize_memory, search_memory, search, search_memory_facts, recall_memories","evidence":"24 discovered tool(s) advertise potentially state-changing or privileged capabilities. Tool names: register_agent, create_watch, list_watches, cancel_watch, check_inbox, read_message, send_message, mark_message, archive_message, resume, confirm_delivery, set_focus, resolve_focus, request_handoff, read_memory_changes, summarize_memory, search_memory, search, search_memory_facts, recall_memories. Classification is description-based and does not prove exploitability.","source_type":"live_probe","sample_size":24,"observed_at":"2026-08-27T00:15:35.239Z","methodology_version":"trust-v1"},{"dimension":"security","metric":"authentication_boundary","status":"observed","value_text":"open","evidence":"Live protocol probe observed auth_state=open. This describes discovery/access behavior; it is not by itself a vulnerability finding.","source_type":"live_probe","sample_size":null,"observed_at":"2026-08-27T00:15:35.239Z","methodology_version":"trust-v1"}],"response_benchmarks":[],"reviewed_field_reports":[],"interpretation":"Dimensions are independent; missing evidence is not a pass; field reports are qualitative, moderated and never votes."}