Every remote server in the official MCP registry, probed live and graded with receipts — the only MCP index where every grade shows its evidence.
30 matches. Categories are keyword-derived from registry metadata — imperfect by design, deterministic by principle.
| # | Server | Grade | Score | Tools |
|---|---|---|---|---|
| 1 | ai.agentdm/agentdm AgentDM: Agent to Agent Communication Platform |
C prov. | 66 | — |
| 2 | ai.i18nagent/i18n-agent i18n-agent |
C prov. | 66 | — |
| 3 | ai.nudg3/brand-intelligence | C prov. | 66 | — |
| 4 | ai.onelore/lore OneLore |
C prov. | 66 | — |
| 5 | ai.secapi/secapi | C prov. | 66 | — |
| 6 | ai.sleepwalker/sleepwalker Sleepwalker |
C prov. | 66 | — |
| 7 | ai.smithery/agentmail | C prov. | 66 | — |
| 8 | ai.smithery/blockscout-mcp-server | C prov. | 66 | — |
| 9 | ai.speko/mcp Speko AI |
C prov. | 66 | — |
| 10 | ai.waystation/mcp | C prov. | 66 | — |
| 11 | app.noemic/noemic-fabs Noemic Fabs |
C prov. | 66 | — |
| 12 | ai.axonagentic/neuroautomata Axon NeuroAutomata |
C prov. | 62 | — |
| 13 | ai.caulo/caulo Caulo |
C prov. | 62 | — |
| 14 | ai.cofoundagent/cofound Cofound |
C prov. | 62 | — |
| 15 | ai.inflowpay.app/inflow | C prov. | 62 | — |
| 16 | ai.lenshub/lenshub LensHub |
C prov. | 62 | — |
| 17 | ai.markettrace/agent-feed MarketTrace agent-feed |
C prov. | 62 | — |
| 18 | ai.optimly/scout Scout by Optimly |
C prov. | 62 | — |
| 19 | ai.outlit/outlit Outlit |
C prov. | 62 | — |
| 20 | ai.plori/plori | C prov. | 62 | — |
| 21 | ai.seaotter/otterscore | C prov. | 62 | — |
| 22 | ai.sendfast/sendfast SendFast |
C prov. | 62 | — |
| 23 | ai.stumpy/agents Stumpy |
C prov. | 62 | — |
| 24 | ai.veecle/chiplab Chiplab |
C prov. | 62 | — |
| 25 | ai.voxplo/voxplo Voxplo |
C prov. | 62 | — |
| 26 | ai.zentrik/mcp Zentrik |
C prov. | 62 | — |
| 27 | app.learnwithagents/learn-with-agents Learn with Agents |
C prov. | 62 | — |
| 28 | app.sentinelx/sentinelx SentinelX |
C prov. | 62 | — |
| 29 | app.superdocs/superdocs | C prov. | 62 | — |
| 30 | app.twiceshy/twiceshy | 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.