Every remote server in the official MCP registry, probed live and graded with receipts — the only MCP index where every grade shows its evidence.
10 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 | ai.appdeploy/deploy-app AppDeploy |
C prov. | 62 | — |
| 5 | ai.smithery/STUzhy-py_execute_mcp | C prov. | 62 | — |
| 6 | app.bauta/bauta Bauta |
C prov. | 62 | — |
| 7 | app.mashop/mcp MaShop MCP |
C prov. | 62 | — |
| 8 | ai.alpic.mcp/alpic-mcp Alpic |
D prov. | 58 | — |
| 9 | ai.simsense/mcp SimSense |
D prov. | 57 | — |
| 10 | ai.paperlantern/code Paper Lantern |
D prov. | 45 | — |
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.