Let ChatGPT, Claude & Cursor use your Mac: email, calendar, iMessage, Teams, files. Local, free.
Communicationv3.0.338streamable-httplocal-mcp.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 244ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2025-06-18, serverInfo LMCP@1.0 |
| tooling | 35 / 35 | tools/list OK: 234 tools e.g. "setup_install"; 234/234 described, 234/234 fully-typed schemas, median description 184 chars |
| latency | 10 / 10 | initialize round-trip 244ms |
| provenance | 15 / 15 | description present; repository linked; version 3.0.338; namespace com.local-mcp matches endpoint/repo |
Score 100/100 · latency 244ms · 234 tools · auth: open
Claude Code:
claude mcp add --transport http local-mcp https://local-mcp.com/mcp
Generic MCP client config:
{ "mcpServers": { "local-mcp": { "type": "http", "url": "https://local-mcp.com/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/com.local-mcp/local-mcp · referral link https://mcpqueen.com/go/com.local-mcp/local-mcp (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/com.local-mcp/local-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 |
|---|---|---|---|
| 2026-07-13 03:30 | A | 100 | 244ms |