Every remote server in the official MCP registry, probed live and graded with receipts — the only MCP index where every grade shows its evidence.
9 matches. Categories are keyword-derived from registry metadata — imperfect by design, deterministic by principle.
| # | Server | Grade | Score | Tools |
|---|---|---|---|---|
| 1 | ai.gemus/gemus Gemus |
C prov. | 66 | — |
| 2 | app.contendeo/contendeo Contendeo |
C prov. | 66 | — |
| 3 | ai.arpi/arpi-mcp ARPI MCP |
C prov. | 62 | — |
| 4 | ai.conveo/conveo Conveo |
C prov. | 62 | — |
| 5 | ai.dragoneye/mcp | C prov. | 62 | — |
| 6 | ai.trackradar/trackradar TrackRadar |
C prov. | 62 | — |
| 7 | ai.viralspin/viralspin ViralSpin |
C prov. | 62 | — |
| 8 | app.hoaster/hoaster | C prov. | 62 | — |
| 9 | app.lightgen/lightgen | C prov. | 62 | — |
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.