Trust Graduation gate: Claude can do real work once Mission decides what it is allowed to do.
Dev & Codev0.1.4streamable-httpclaude.gomission.io repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 755ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo mission@0.1.0-demo |
| tooling | 35 / 35 | tools/list OK: 29 tools e.g. "mission_open_cockpit"; 29/29 described, 29/29 fully-typed schemas, median description 139 chars |
| latency | 7 / 10 | initialize round-trip 755ms |
| provenance | 15 / 15 | description present; repository linked; version 0.1.4; namespace io.github.gomission matches endpoint/repo |
Score 97/100 · latency 755ms · 29 tools · auth: open
Claude Code:
claude mcp add --transport http mcp https://claude.gomission.io/mcp/
Generic MCP client config:
{ "mcpServers": { "mcp": { "type": "http", "url": "https://claude.gomission.io/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.gomission/mcp · referral link https://mcpqueen.com/go/io.github.gomission/mcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.gomission/mcp)
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.
Email alerts when the grade changes or the endpoint stops answering. Double-opt-in, one-click unwatch, free while in beta.
| When (UTC) | Grade | Score | Latency |
|---|---|---|---|
| 2026-07-14 01:45 | A | 97 | 755ms |