io.github.truepointmarketingpartners-dotcom/claim-grounding

Est-ce que io.github.truepointmarketingpartners-dotcom/claim-grounding est sûr ?

Au dernier audit MCP Hub, le serveur MCP « io.github.truepointmarketingpartners-dotcom/claim-grounding » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 4 outils

• check_answer≈ 1532 tokens

  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confidence, quote, source URL, sentence span and suggested_correction (quoted only from cited sources when contradicted/outdated), plus an answer-level summary with overall_verdict, counts and problem_sentences.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.

  Paramètres, retour & exemple (3)

  Paramètres

  • answer · string · requis
    The full answer text to fact-check. Each factual sentence is checked separately.
  • sources · array · optionnel
    Optional. Up to 10 sources of your own, used as extra evidence next to the public sources and cited with provider and source_type "caller". The response lists what was used in sources_used.
  • sources_only · boolean · optionnel
    Optional. true = judge the claim only against your sources (no public-source lookups). Needs a non-empty sources array.

  Exemple d'appel

  {"name": "check_answer", "arguments": {"answer": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tool": "texte", "result": {}, "status": "payment_required", "message": "texte", "payment": {}}}

• deep_verify≈ 1024 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • answer · string · requis
    The claim or short text to verify (up to three claims are checked).
  • sources · array · optionnel
    Optional. Up to 10 sources of your own, used as extra evidence next to the public sources and cited with provider and source_type "caller". The response lists what was used in sources_used.
  • sources_only · boolean · optionnel
    Optional. true = judge the claim only against your sources (no public-source lookups). Needs a non-empty sources array.

  Exemple d'appel

  {"name": "deep_verify", "arguments": {"answer": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tool": "texte", "result": {}, "status": "payment_required", "message": "texte", "payment": {}}}

• extract_claims≈ 1036 tokens

  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.

  Paramètres, retour & exemple (1)

  Paramètres

  • text · string · requis
    The text to split into claims, for example a chatbot answer. Up to a few thousand characters.

  Exemple d'appel

  {"name": "extract_claims", "arguments": {"text": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tool": "texte", "result": {}, "status": "payment_required", "message": "texte", "payment": {}}}

• verify_claim≈ 1334 tokens

  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.

  Paramètres, retour & exemple (3)

  Paramètres

  • claim · string · requis
    One factual sentence to check.
  • sources · array · optionnel
    Optional. Up to 10 sources of your own, used as extra evidence next to the public sources and cited with provider and source_type "caller". The response lists what was used in sources_used.
  • sources_only · boolean · optionnel
    Optional. true = judge the claim only against your sources (no public-source lookups). Needs a non-empty sources array.

  Exemple d'appel

  {"name": "verify_claim", "arguments": {"claim": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}], "structuredContent": {"tool": "texte", "result": {}, "status": "payment_required", "message": "texte", "payment": {}}}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://claim-grounding.prospectintel.workers.dev/mcp