Skip to content

Claim Grounding

by truepointmarketingpartners-dotcom · remote · no sign-in to list tools · v1.4.7 · published by GitHub user truepointmarketingpartners-dotcom

Fact-check AI answers with cited sources. Pay per call in USDC on Base via x402.

Changes · 4

4 tools: 4 change things.

Scanned Oct 21, 2026

3 checks matched something in the tool definitions. No finding is not a safety guarantee. How the checks work.

claude mcp add --transport http claim-grounding https://claim-grounding.prospectintel.workers.dev/mcp

Findings

Matches of fixed checks, with the text they matched.

3 info
  • The input schema at properties.sources.items.properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

    What this check looks for
  • The input schema at properties.sources.items.properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

    What this check looks for
  • The input schema at properties.sources.items.properties.url.description mentions "credentials".

    Matched text

    inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

    What this check looks for

Tools

Open a tool for its reasons and full description. Descriptions are the publisher's own words, shown as they are.

4 tools

Changes things 4Claude Code: ask
  • check_answerFact-check a whole answer: extracts every checkable claim and verifies each against Wikipedia, plus Wikidata structured facts for dates, numbers, quantities, ordinals and records.1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The input schema at properties.sources.items.properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

      What this check looks for
    Description, as the server wrote it
    Fact-check a whole answer: extracts every checkable claim and verifies each against Wikipedia, plus Wikidata structured facts for dates, numbers, quantities, ordinals and records. Returns per-claim verdict, confidence, quote, source URL, sentence span and suggested_correction (quoted only from cited sources when contradicted/outdated), plus an answer-level summary with overall_verdict, counts and problem_sentences. Abstained rather than guessed. Use to audit chatbot or RAG output. Price: $1.00 USDC on Base per call via x402; this MCP call returns payment instructions and POST /v1/check_answer returns the results. Read-only.

    Annotations the server declares

    • title: Check answer
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • deep_verifyUse when a claim is high-stakes, or when check_answer or extract_claims marks it unsure (their next_step gives the exact request).1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The input schema at properties.sources.items.properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

      What this check looks for
    Description, as the server wrote it
    Use when a claim is high-stakes, or when check_answer or extract_claims marks it unsure (their next_step gives the exact request). Verifies up to three claims against Wikipedia, Wikidata, Google News, Europe PMC, FRED and SEC EDGAR; returns verdict, confidence, evidence for and against with URLs, and flags contradictions. Async: poll GET /v1/jobs/{job_id} free. $0.75 USDC on Base via x402. Read-only.

    Annotations the server declares

    • title: Deep verify
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • extract_claimsSplit a text (for example an AI-generated answer) into atomic factual claims.No findings

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
    Description, as the server wrote it
    Split a text (for example an AI-generated answer) into atomic factual claims. Each claim includes span, grounding_required, claim_type (number|date|quantity|quote|named_entity_fact|comparison|opinion|prediction|other), check_worthiness (high|medium|low), and the source sentence. Hedges are stripped, pronouns are resolved across sentences, and compound sentences are split. Questions, greetings, opinions and predictions are marked grounding_required false. Use before verify_claim. Price: $0.05 USDC on Base per call via x402; this MCP call returns payment instructions and POST /v1/extract_claims returns the claims. Read-only.

    Annotations the server declares

    • title: Extract claims
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true
  • verify_claimCheck one factual claim against public Wikipedia sources and return a verdict (supported, contradicted, outdated, mixed or insufficient_evidence), a confidence score, a short reaso…1 finding

    Why it is in this group

    • Nothing in its name or description says what it does, so it is counted as a write.
    • The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.

    Findings

    • Info

      The input schema at properties.sources.items.properties.url.description mentions "credentials".

      Matched text

      inputSchema.properties.sources.items.properties.url.description: "...teral hosts, custom ports and URLs with credentials are rejected (HTTP 400, not charged). W..."

      What this check looks for
    Description, as the server wrote it
    Check one factual claim against public Wikipedia sources and return a verdict (supported, contradicted, outdated, mixed or insufficient_evidence), a confidence score, a short reason, the supporting quote and the source URL. Says insufficient_evidence instead of guessing. Price: $1.00 USDC on Base per call via x402; this MCP call returns payment instructions and the paid HTTP route POST /v1/verify_claim returns the verdict. For a multi-source check use deep_verify. Read-only.

    Annotations the server declares

    • title: Verify claim
    • readOnlyHint: true
    • destructiveHint: false
    • idempotentHint: true
    • openWorldHint: true

This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.

Install

Pinned to version 1.4.7. Values in angle brackets are yours to fill in.

claude mcp add --transport http claim-grounding https://claim-grounding.prospectintel.workers.dev/mcp

Run in a terminal.

Claude Code permissions

Allow the reads, ask before a change, deny the deletes. Paste into .claude/settings.json.

.claude/settings.json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__claim-grounding__extract_claims",
      "mcp__claim-grounding__verify_claim",
      "mcp__claim-grounding__check_answer",
      "mcp__claim-grounding__deep_verify"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. It assumes the server is installed as claim-grounding. Review it before you use it.