Skip to main content
Glama
catqualia-ledger-mcp

catqualia-ledger-mcp

Official

catqualia-ledger-mcp

An MCP server that lets an agent check a claim against a real, published falsification ledger instead of guessing.

Agents are increasingly asked to verify their own output. Most have nowhere to verify it against. This server is a concrete answer: 16,217 claims that were actually run against ground truth, each recorded with the measurement that would have refuted it, the value measured, and the verdict — including 5,837 the system refuted against its own work.

What is in the ledger

Computed from the bundled ledger.jsonl.gz at call time, never hardcoded:

parseable records

16,217

distinct checks

324

records carrying a pre-registered refutation threshold

16,194 (99.9%)

verdicts REFUTED

5,837

verdicts CONFIRMED

5,520

verdicts UNVERIFIED

4,815

checks re-run at least twice

277

verdict transitions

79

hardening / loosening

38 / 38 — net 0

The last line is the point. Re-run the checks and classify every verdict that moved: CONFIRMED -> REFUTED after a check is hardened means the instrument had been fooled and stopped being fooled (a hardening event); the reverse is a loosening event. The signed net measures whether a system's ability to catch its own false claims is improving or degrading.

It is currently zero. That is published because reporting only the +38 half would be a metric tuned to its owner — which is the exact failure the ledger exists to detect.

Related MCP server: claimidx

Install

uvx catqualia-ledger-mcp        # run without installing
# or
pip install catqualia-ledger-mcp

No dependencies. Python 3.9+. Implements MCP over stdio as newline-delimited JSON-RPC 2.0.

Configure

{
  "mcpServers": {
    "catqualia-ledger": {
      "command": "uvx",
      "args": ["catqualia-ledger-mcp"]
    }
  }
}

Tools

query_claim(query, verdict?, limit?)

Search the ledger. Returns the claim, its refutation threshold, the measured value, the method, and the verdict.

get_verdict(check?, claim?)

The recorded verdict for a named check. If a check ran more than once, all verdicts are returned in ledger order — a change between them is a ratchet event. A claim that is not in the ledger returns found: 0, never a plausible guess.

what_would_refute(query?, limit?)

The pre-registered threshold: the measurement that would have killed each claim, recorded before the outcome was known. Use it to test whether a claim is falsifiable at all, rather than whether it is currently believed.

verifier_drift_net()

The ratchet, recomputed from the ledger: re-runs, transitions, hardening, loosening, signed net, and the definition of what the number means.

citation_block(slug?)

BibTeX plus schema.org ScholarlyArticle JSON for a CatQualia publication, with the DOI resolved, so citing agents cite correctly. Call with no slug to list what is available.

Design rules this server follows

These are deliberate, and they are the reason it is worth trusting:

  • Every number is computed from the bundled ledger at call time. Nothing is cached from a summary or a blog post.

  • UNVERIFIED is returned as UNVERIFIED. It is never rounded up to a verdict, in either direction.

  • A miss returns a miss. If a claim is not in the ledger the server says so and explains that absence is not evidence either way. It does not infer.

  • The net ratchet is returned signed, including when it is zero.

  • A slug match is exact-first. Substring matching is not safe for a citation tool: "thesis" is a substring of "synthesis", which once returned the wrong DOI. Matching is exact → prefix → contains → word-boundary on title.

Licence

Code: CatQualia Open-Or-Pay Licence (COPL) v1.0 — free for research, individuals and academia with attribution; commercial use requires either opening the derivative stack or a commercial waiver. See LICENSE.

Ledger data: CatQualia Structural Isomorphism License (CSIL) v3.0 — https://catqualia.com/licensing.

Citation

@software{catqualia_ledger_mcp,
  title  = {catqualia-ledger-mcp: an MCP server for the CatQualia falsification ledger},
  author = {Betances, Christopher},
  year   = {2026},
  url    = {https://github.com/OpeningBlackBox/catqualia-ledger-mcp},
  note   = {16,217 pre-registered claims; verifier ratchet net zero}
}

Available Tools

5 tools
citation_blockA

Return a ready-to-use BibTeX entry and schema.org ScholarlyArticle JSON for a CatQualia publication, so that citing agents cite correctly and resolve the DOI. Call with no slug to list available slugs.

Inputs: slug.

get_verdictA

Retrieve the recorded verdict for a named check, or find claims containing a phrase. If a check was run more than once, all verdicts are returned in ledger order — a change between them is a ratchet event. Never infers a verdict for a claim that is not in the ledger.

Inputs: check, claim.

query_claimB

Search the CatQualia falsification ledger for claims matching a string, optionally filtered by verdict. Returns the claim, the pre-registered threshold that would refute it, the measured value, and the verdict. The ledger holds 16,217 measured claims including 5,837 the system refuted against its own ground truth.

Inputs: limit, query, verdict.

verifier_drift_netA

Measure the verifier ratchet: whether a system's ability to catch its own false claims is improving or degrading. Re-runs checks and classifies every verdict transition as hardening or loosening, returning the signed net. Currently 277 checks re-run, 79 transitions, 38 hardening, 38 loosening, net zero.

Inputs: no named parameters.

what_would_refuteA

Return the pre-registered refutation threshold for matching claims: the measurement that would have killed each claim, recorded before the outcome was known. 16,194 of 16,218 ledger records carry one. Use this to test whether a claim is falsifiable at all.

Inputs: limit, query.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 5 tools

    Disambiguation4/5

    The tools are mostly distinct: query_claim returns full claim records, get_verdict focuses on verdict retrieval, what_would_refute provides thresholds, verifier_drift_net measures transitions, and citation_block handles citations. There is some overlap between query_claim and get_verdict in searching by phrase, but the purposes are clearly different enough to avoid significant confusion.

    Naming Consistency2/5

    Naming conventions are inconsistent. query_claim and get_verdict follow a verb_noun pattern, but what_would_refute is a question phrase, verifier_drift_net is a noun compound, and citation_block is also noun_noun. This mixed style makes it harder to predict tool names and reduces coherence.

    Tool Count5/5

    With only 5 tools, the server is tightly scoped to its ledger domain. Each tool covers a distinct need—searching, verdicts, thresholds, drift analysis, and citations—without redundancy or bloat.

    Completeness4/5

    The tool surface covers the core operations for querying and analyzing the ledger: search, verdict retrieval, threshold lookup, drift measurement, and citation generation. Minor gaps exist, such as no explicit tool to list all claims or add new ones, but the apparent read-only purpose is well-served.

    Maintenance

    ActivityStale
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      Enables AI agents to query a public signed ledger of known failures and fixes before retrying, then ingest, confirm, fail, and share dense claims so subsequent agents avoid paying the same cost.
      29
      486 PyPI
      3
      Apache 2.0
    • A
      license
      A
      quality
      C
      maintenance
      Enables agents and clients to fact-check factual claims against live web sources, returning citable verdicts with source details and cryptographically signed receipts for downstream verification.
      1
      61 npm
      MIT
    • A
      license
      Not graded
      quality
      B
      maintenance
      Enables deterministic verification of AI agent decisions and actions, providing PASS/FAIL/ABSTAIN verdicts with replayable proofs and an optional signed receipt ledger.
      Apache 2.0