Every remote server in the official MCP registry, probed live and graded with receipts — the only MCP index where every grade shows its evidence.
8 matches. Categories are keyword-derived from registry metadata — imperfect by design, deterministic by principle.
| # | Server | Grade | Score | Tools |
|---|---|---|---|---|
| 1 | ai.thinkneo/control-plane ThinkNEO Control Plane |
A | 97 | 68 |
| 2 | ai.scamverify/mcp ScamVerify Threat Verification |
C prov. | 66 | — |
| 3 | ai.bluenexus/universal-mcp BlueNexus Universal MCP |
C prov. | 62 | — |
| 4 | ai.bodenrichtwert/mcp bodenrichtwert.ai — Amtliche Bodenrichtwerte |
C prov. | 62 | — |
| 5 | ai.byteray/byteray-mcp ByteRay AI |
C prov. | 62 | — |
| 6 | ai.complyhat/compliance ComplyHat |
D prov. | 57 | — |
| 7 | ai.rfp/rfp-ai RFP.ai |
D prov. | 57 | — |
| 8 | ai.aisecuritygateway/mcp-gateway AI Security Gateway — MCP Gateway |
D prov. | 49 | — |
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.