Loading…
Deterministic signed verification of numeric and financial claims for AI agents and spreadsheets.
Review before connecting
The findings on this server are worth reviewing before you connect an agent to it.
Scanned 7 days ago Due for re-check
A server can change after it's graded. Re-run the automated scan to refresh this report.
This grade is deterministic and reproducible: the same server surface always yields the same grade under a given algorithm version. It is a real automated assessment computed by the MCPGrade engine from what the probe actually observed — not a fabricated or opinion score. It is not a manual human pentest, so it can miss context-specific risks.
Every signal below was measured directly by the automated probe. The grade is derived only from evidence like this — nothing is assumed.
The NumProof MCP server exposes 4 tools across a range of capabilities. Its published description reads: "Deterministic signed verification of numeric and financial claims for AI agents and spreadsheets". It communicates over Streamable HTTP using the 2026-07-28 protocol revision, and does not require authorization to connect. MCPGrade currently rates NumProof C+ — the findings are worth reviewing before you connect an agent to it. Its most notable finding was "No authorization on a public remote server". This report is a deterministic, reproducible automated assessment: the same observed surface always yields the same grade under a given algorithm version, and it is refreshed as new scans arrive and free to read — but it is not a substitute for a manual human security review. Always re-check NumProof's advertised tools, transport security, and authorization posture before connecting an autonomous agent or sharing sensitive context with it.
Add NumProof to an MCP client using the endpoint below. Review the grade and findings above before granting an autonomous agent access.
MCP endpoint
https://numproof.com/mcpStreamable HTTP transport. This is the MCP endpoint, not a website — paste it into your MCP client server list rather than a browser.
Captured passively during the read-only scan. Click any value to find servers that match it.
The tools this server advertises via tools/list — names, purposes, and the parameters each accepts, exactly as enumerated read-only.
Exactly verify a math/finance claim (VERIFY/REFUTE/ABSTAIN) with a counterexample when false. Use before trusting any AI-produced number, sum, percentage, or formula.
Audit spreadsheet-like rows for footing, balance-sheet ties, common margins, and cell provenance.
Compare two report versions by numeric row labels with provenance.
Evaluate threshold/covenant rules over spreadsheet-like rows with provenance. Use either rules or rule_pack.
Sorted worst-first. Each finding shows its severity, what it means, its OWASP MCP Top-10 mapping, and a recommended fix — the check id links to the exact methodology row that produced it.
The server accepts tool enumeration (and likely invocation) with no authentication.
RecommendationRequire OAuth 2.1 authorization for any server exposing non-public tools.
Temporary email for AI agents — create inboxes, wait for verification emails, extract OTPs, and automate signup flows.
Runnable, versioned lists agents can search, read, create, and update — git under the hood.
Convert a written schedule into a subscribable calendar link for Apple, Google, and Outlook.
Acornonaut's MCP server for AI-powered YouTube-to-flashcard conversion with spaced repetition.
Analyze chess positions using powerful engines like Stockfish, Leela, and Maia. Retrieve games, puzzles, and opening statistics directly from Lichess and specialized databases. Visualize move
Your Team0 AI Chief of Staff, reachable from any agent — answers, acts, and coordinates.