Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets.
Dev & Codev0.1.1streamable-httpnumproof.com repository
| Criterion | Points | Observed |
|---|---|---|
| reachability | 25 / 25 | HTTP 200, initialize accepted in 126ms |
| protocol | 15 / 15 | valid JSON-RPC initialize result, protocolVersion 2024-11-05, serverInfo NumProof@1.0.0 |
| tooling | 35 / 35 | tools/list OK: 4 tools e.g. "verify_claim"; 4/4 described, 4/4 fully-typed schemas, median description 108 chars |
| latency | 10 / 10 | initialize round-trip 126ms |
| provenance | 15 / 15 | description present; repository linked; version 0.1.1; namespace io.github.projecttron matches endpoint/repo |
Score 100/100 · latency 126ms · 4 tools · auth: open
Claude Code:
claude mcp add --transport http numproof https://numproof.com/mcp
Generic MCP client config:
{ "mcpServers": { "numproof": { "type": "http", "url": "https://numproof.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/io.github.projecttron/numproof · referral link https://mcpqueen.com/go/io.github.projecttron/numproof (counts as “routed via the queen”).
Live badge, re-probed continuously — put it in your README:
[](https://mcpqueen.com/s/io.github.projecttron/numproof)
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 18:45 | A | 100 | 126ms |