Operational grades show whether a server connects and describes usable tools. Separate Trust Receipts show what has actually been observed about security and access boundaries, data integrity, citations, advertised claims, response quality, and real-world use.
21 matches. Categories are keyword-derived from registry metadata — imperfect by design, deterministic by principle.
| # | Server | Grade | Score | Tools |
|---|---|---|---|---|
| 1 | ai.aient/mcp | C prov. | 66 | — |
| 2 | ai.smithery/docfork-mcp | C prov. | 66 | — |
| 3 | ai.smithery/Nekzus-npm-sentinel-mcp | C prov. | 66 | — |
| 4 | builders.bridgetown/bridge-town Bridge Town |
C prov. | 66 | — |
| 5 | com.avalara/docs Avalara Developer Documentation |
C prov. | 66 | — |
| 6 | com.githits/githits GitHits |
C prov. | 66 | — |
| 7 | com.instapods/instapods InstaPods |
C prov. | 66 | — |
| 8 | ai.trendsmcp/trends Trends MCP |
C | 65 | — |
| 9 | com.gitlab/mcp | C prov. | 63 | — |
| 10 | ai.appdeploy/deploy-app AppDeploy |
C prov. | 62 | — |
| 11 | ai.smithery/STUzhy-py_execute_mcp | C prov. | 62 | — |
| 12 | ai.synlake/synlake Synlake |
C | 62 | — |
| 13 | ai.trendsmcp/npm npm Trends MCP |
C | 62 | — |
| 14 | app.mashop/mcp MaShop MCP |
C prov. | 62 | — |
| 15 | app.vibecom/growth VibeCom Growth Autopilot |
C prov. | 62 | — |
| 16 | co.tenderly/tenderly-mcp | C prov. | 62 | — |
| 17 | com.arcjet/mcp Arcjet |
C prov. | 62 | — |
| 18 | com.consentlayer/mcp ConsentLayer |
C prov. | 62 | — |
| 19 | com.emtailabs/xray-vision XRay-Vision |
C prov. | 62 | — |
| 20 | com.genmb/genmb GenMB |
C prov. | 62 | — |
| 21 | com.matterfact/matterfact matterfact |
C prov. | 62 | — |
Claim your live grade badge for your README, and get an email the moment your grade moves or your endpoint stops answering — find your server above and hit Watch. Free while in beta.
Ask the queen before you connect to a stranger:claude mcp add --transport http mcpqueen https://mcpqueen.com/mcp
Evidence-backed shortlists for high-intent decisions—not generated pages for every keyword.
Data & DatabasesWeb & SearchScience & HealthFinance & CryptoDev & Code Security & trust evidence
Each server is probed live over streamable HTTP: reachability (25) — does initialize succeed; auth-gated servers earn partial credit only if they advertise WWW-Authenticate so clients can discover OAuth. protocol (15) — valid JSON-RPC handshake; deprecated SSE transport is penalized. tooling (35) — tools/list works, share of tools with descriptions and fully-typed input schemas, median description depth. latency (10) — initialize round-trip. provenance (15) — registry metadata completeness and whether the reverse-DNS namespace actually matches the serving domain. Scores scale to what is verifiable; unverifiable dimensions mark the grade provisional rather than guessing. Every point carries the verbatim observation that earned it. No stars, no votes, no pay-to-rank — probes only.
Trust Receipts are separate from the operational grade. Discovery records advertised security-sensitive capabilities, access caveats, citation promises, and corpus-size claims. Safe, read-only response audits sample eligible tools and test whether calls are usable, whether returned PMIDs/DOIs resolve against authoritative sources, and whether an apparently successful response actually contains an upstream error. Every observation includes its date, source type, sample size where applicable, and methodology version. No synthetic trust score is assigned, and absence of an observation means unaudited—not safe.
Get an email when a server's grade changes or its endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.