Humanities Helping Hands checker
Server Details
121 machine-proven math facts, plus 49 real-world claims with machine-checked arithmetic
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 3 tools
Each tool targets a distinct action+resource: check_claim verifies claims inside supplied text, lookup_fact searches a fact library, and search_attempts searches only past P vs NP attempts. The only soft overlap is between check_claim's handling of open problems and search_attempts' P vs NP focus, but the descriptions make the boundary (verdict vs warning-sign search) reasonably clear.
All three tools follow a clean verb_noun snake_case pattern: check_claim, lookup_fact, search_attempts. No mixed conventions or vague standalone verbs.
Three tools is on the thin side, but the server's scope is deliberately narrow (mechanical claim checking plus two lookup surfaces), and each tool earns its place. It is slightly under-provisioned rather than bloated.
The surface covers the core read-only workflow: check a claim, look up known facts, and check whether an argument has already been attempted. Minor gaps exist around lifecycle operations (no tool to add facts or register new attempts), but these may be intentional for a checker and agents can work around them.
Available Tools
3 toolscheck_claimCheck a claimARead-onlyIdempotentInspect
Find the claims in a text and check the ones plain code can: arithmetic (PROVEN or FALSIFIED), primes, unit conversions. A famous unsolved problem (P vs NP, the Riemann hypothesis) is OPEN. Anything else is NOT CHECKED, which never means false, with a next step.
Inputs: text (required).
lookup_factLook up a proven factARead-onlyIdempotentInspect
Search the library of machine-checked facts. Compact by default (claim start, label, receipt link); set detail true for the full wording.
Inputs: query (required), detail, max_results.
search_attemptsSearch past P vs NP attemptsARead-onlyIdempotentInspect
Search the list of past attempts at P vs NP. Rows are labeled CHECKED, REASONED or NOT TRACED. A match is a warning sign, never a verdict.
Inputs: query (required), max_results.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Register of AI claims in mathematics, graded by the evidence behind each. Paid Lean proof checks.
Deterministic claim verification with receipts across ~60 domains. No model in the loop.
Deterministic signed verification of numeric & financial claims for AI agents & spreadsheets.
Architecture compiler for AI code. 11 tools, 92 actions, 872 Lean4 proofs, 100/100 self-cert.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables rigorous, machine-checked mathematical proving and proof review through 23 local tools that formalize propositions, verify each inference step with SMT and symbolic solvers, search for counterexamples, and run exact number-theoretic and high-precision arithmetic. Verdicts are strictly separated into proven, refuted, inconclusive, verified, sound_with_gaps, and flawed, so unproven steps are disclosed rather than hidden.MIT
- AlicenseNot gradedqualityBmaintenanceEnables rigorous, auditable mathematical proving with machine-checked steps, honestly distinguishing proven, refuted, and inconclusive results while disclosing unverified gaps.1MIT
- AlicenseAqualityBmaintenanceAirtight math tools an AI uses over MCP — 3.7M-theorem search, PSLQ constant ID, OEIS, real Lean kernel checks, applicability checklists. No LLM inside, no API key.1252 PyPI14Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to verify claims deterministically by computing arithmetic, ratios, and dates and matching statements against provided sources, returning a confidence ladder of certain, source-backed, or unverifiable.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.