MCP QUEEN
io.github.Termi24/eyeot-erp B
ERP français avec serveur MCP natif : plus de 1 800 actions métier auto-générées via OpenAPI.
Dev & Codev1.1.1streamable-httperp.eyeot.fr repository
Grade evidence — probed 2026-07-13 19:32 UTC
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 1561ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo eyeot-erp@1.0.0 |
| tooling | 30 / 35 | tools/list OK: 33 tools e.g. "whoami"; 33/33 described, 33/33 fully-typed schemas, median description 24 chars |
| latency | 4 / 10 | initialize round-trip 1561ms |
| provenance | 15 / 15 | description present; repository linked; version 1.1.1; namespace io.github.Termi24 matches endpoint/repo |
Score 89/100 · latency 1561ms · 33 tools · auth: open
Connect your agent
Claude Code:
claude mcp add --transport http eyeot-erp https://erp.eyeot.fr/api/v1/mcp
Generic MCP client config:
{ "mcpServers": { "eyeot-erp": { "type": "http", "url": "https://erp.eyeot.fr/api/v1/mcp" } } }
MCP Queen is a graded index, not a middleman — your agent connects directly to the server above. Check the grade and evidence first; that's the point.
Share this server: permalink https://mcpqueen.com/s/io.github.Termi24/eyeot-erp · referral link https://mcpqueen.com/go/io.github.Termi24/eyeot-erp (counts as “routed via the queen”).
Own this server? Embed your grade badge
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.Termi24/eyeot-erp)
Think the grade is wrong? Fix the finding the evidence shows, then the next probe cycle picks it up automatically (full cycle ≈ 3 days) — or open a dispute via the MCP endpoint.
Queen Watch
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
Probe history
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-13 19:32 | B | 89 | 1561ms |