πŸ‘‘

MCP QUEEN

The Graded Registry

Every remote server in the official MCP registry, probed live and graded with receipts β€” the only MCP index where every grade shows its evidence.

16246servers indexed
7735remote endpoints
772graded (rolling)
208grade A
67%reachable
385msmedian latency
SortBestWorstJust probedMost toolsFastest
GradeAllA (208)B (3)C (198)D (107)F (256)Provisional
CategoryAll categoriesOther (204)AI & Agents (149)Web & Search (137)Cloud & Infra (65)Productivity (43)Dev & Code (35)Data & Databases (29)Finance & Crypto (27)Communication (21)Media & Design (19)Commerce (17)Security (13)Science & Health (13)

13 matches. Categories are keyword-derived from registry metadata β€” imperfect by design, deterministic by principle.

#ServerGradeScoreLatencyToolsAuthProbed
1 ai.thinkneo/control-plane
ThinkNEO Control Plane
Security
A 97
772ms 68 open 07-12 17:47
2 app.eurocomply/compliance
EuroComply β€” EU Regulatory Compliance
Security
A 97
262ms 4 open 07-12 18:48
3 ai.scamverify/mcp
ScamVerify Threat Verification
Security
C prov. 66
314ms β€” auth-wellbehaved 07-12 15:46
4 app.thoughtspot/mcp-server
Security
C prov. 66
453ms β€” auth-wellbehaved 07-12 19:31
5 ai.bluenexus/universal-mcp
BlueNexus Universal MCP
Security
C prov. 62
460ms β€” auth-wellbehaved 07-12 14:18
6 ai.bodenrichtwert/mcp
bodenrichtwert.ai β€” Amtliche Bodenrichtwerte
Security
C prov. 62
61ms β€” auth-wellbehaved 07-12 14:18
7 ai.byteray/byteray-mcp
ByteRay AI
Security
C prov. 62
72ms β€” auth-wellbehaved 07-12 14:19
8 ai.complyhat/compliance
ComplyHat
Security
D prov. 57
1120ms β€” auth-wellbehaved 07-12 14:19
9 ai.rfp/rfp-ai
RFP.ai
Security
D prov. 57
1191ms β€” auth-wellbehaved 07-12 15:31
10 app.clearpolicy/clearpolicy
ClearPolicy
Security
D prov. 57
756ms β€” auth-wellbehaved 07-12 18:48
11 app.openclip/openclip
OpenClip
Security
D prov. 57
746ms β€” auth-wellbehaved 07-12 19:03
12 ai.aisecuritygateway/mcp-gateway
AI Security Gateway β€” MCP Gateway
Security
D prov. 49
174ms β€” auth-bare 07-12 14:18
13 app.locize.mcp/server
Locize
Security
D prov. 45
694ms β€” auth-bare 07-12 19:03

Methodology

Each server is probed live over streamable HTTP: reachability (25) β€” does initialize succeed; auth-gated servers earn partial credit only if they advertise WWW-Authenticate so clients can discover OAuth. protocol (15) β€” valid JSON-RPC handshake; deprecated SSE transport is penalized. tooling (35) β€” tools/list works, share of tools with descriptions and fully-typed input schemas, median description depth. latency (10) β€” initialize round-trip. provenance (15) β€” 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 β€” probes only.