The evidence layer for MCP: live operational grades plus Trust Receipts for every registry server.
Scored across 7 tools
The tools mostly have distinct purposes: get_server_grade and get_trust_receipt both retrieve detailed info about a single server, which could be confused, but descriptions clarify that one is grade-focused and the other is evidence-receipt-focused. Search tools are clearly differentiated by target (servers vs tools vs trust evidence), and submit_feedback is unique.
All tool names follow a consistent verb_noun pattern: get_server_grade, get_trust_receipt, list_grades, search_servers, search_tools, search_trust_evidence, submit_feedback. Verbs are consistent (get, list, search, submit) and nouns are clear, creating a predictable and readable API.
With 7 tools, the set is well-scoped for a registry/search/feedback server. Each tool addresses a distinct need: retrieving grades, retrieving receipts, listing top servers, searching servers, tools, trust evidence, and submitting feedback. No tool feels redundant or excessive for the domain.
The tool surface covers the main workflows: searching and retrieving server grades and evidence, searching tools and trust evidence, and submitting feedback. Minor gaps exist, such as no ability to list all tools or all trust evidence without a search query, but the provided search functions are flexible enough to cover most needs.
Get the full grade and verbatim probe evidence for one MCP server, by its official registry name (e.g. 'com.healthai/radar').
Inputs: name (required). Returns: grade, score, version, evidence, +10 more
Get one MCP server's complete evidence receipt: operational grade, deterministic security/data-integrity/citation/claim observations, and reviewed real-usage field reports. Missing observations are explicitly unaudited, never treated as a pass.
Inputs: name (required). Returns: server, audit_state, observations, evidence_page, +5 more
List the top graded MCP servers from the mcpqueen registry (deterministic probe grades with evidence). Returns grade, score 0-100, latency, tool count and auth state per server.
Inputs: limit. Returns: results, returned, safety_notice
Search the MCP evidence registry using a natural multi-word task (e.g. 'reliable no-auth drug interaction server with citations'). Tokenizes and expands common synonyms, ranks metadata plus observed tool descriptions, and supports operational-grade/auth/latency/category filters. Use get_trust_receipt or search_trust_evidence for security, data, citation, claim, and response evidence.
Inputs: query (required), auth, limit, category, +2 more. Returns: message, results, safety_notice, feedback_reminder, +1 more
Search across the actual tools that graded MCP servers expose (their tool names and descriptions, captured live from tools/list) — not just server metadata. Use this when you need a specific capability or data type, e.g. 'get weather', 'query postgres', 'device recall', 'FDA 510k'. Returns the matching tools with the server that offers each, its grade, and the remote endpoint so you can connect directly.
Inputs: query (required), auth, limit, category, +2 more. Returns: message, results, safety_notice, feedback_reminder, +1 more
Search published MCP trust evidence and reviewed real-usage field reports. Use for questions such as which servers expose citations, have access caveats, make unverifiable corpus claims, or show security concerns. Returns verbatim observations with dates and source type, not a synthetic trust score.
Inputs: query (required), limit, status, dimension. Returns: query, results, returned, safety_notice, +1 more
Submit a field report about an MCP server you have actually used (what worked, what failed, surprising behavior). Reports are quarantined for human review and never auto-published.
Inputs: report (required), server_name (required), agent_name. Returns: status, message, server_name, safety_notice
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Remote MCP for MCP consent scope receipt, structured receipts, audit logs, and reviewer-ready eviden
Independent trust scores, tool surfaces and change history for MCP servers.
Trust checks and Data Passports: identity, co-signed receipts, scores, badges, and custody evidence.
28 MCP servers behind one endpoint: earth, sky, policy, records and research
Add one secure layer between your agents and this server.