Claim Grounding
Server Details
Fact-check AI answers with cited sources and quick_check. Pay per call in USDC via x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- Repository
- truepointmarketingpartners-dotcom/prospect-intelligence
- GitHub Stars
- 0
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 5 tools
extract_claims and check_answer are clearly distinct entry points, but quick_check, verify_claim and deep_verify all verify claims and differ only by price/source depth (and the price ladder is odd: deep_verify at $0.75 covers three claims with six sources while verify_claim at $1.00 covers one with Wikipedia only). The descriptions do provide a routing ladder, but an agent choosing a verification tier can easily misselect.
All names are lowercase snake_case and readable, but the pattern isn't uniform: check_answer, extract_claims and verify_claim follow verb_noun while quick_check and deep_verify use a modifier_verb form. Minor deviation, still predictable enough.
Five tools is a well-scoped surface for a claim-verification service: one extraction tool and a small tiered verification ladder plus a whole-answer auditor. Each tool has a defensible role, no obvious filler.
The surface covers extraction, single-claim checks at three depths, and whole-answer auditing, which is good lifecycle coverage for grounding. The gap is the async flow: deep_verify instructs polling GET /v1/jobs/{job_id} but no job-status tool exists, leaving an agent to make an unlisted HTTP call to collect results.
Available Tools
5 toolscheck_answerCheck answerARead-onlyIdempotentInspect
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confidence, quote, source URL, sentence span and suggested_correction (quoted only from cited sources when contradicted/outdated), plus an answer-level summary with overall_verdict, counts and problem_sentences.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.
Inputs: answer (required), sources, sources_only. Returns: tool, result, status, message, +1 more
deep_verifyDeep verifyARead-onlyIdempotentInspect
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.
Inputs: answer (required), sources, sources_only. Returns: tool, result, status, message, +1 more
extract_claimsExtract claimsARead-onlyIdempotentInspect
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. Up to 3 checkable factual claims (opinions skipped) get a next_step: a ready-to-send quick_check request ($0.15, fast verdict with 1-2 sources), with deep_verify ($0.75) and verify_claim ($1.00) bodies in next_step.alternatives, so you can check them in one more call. 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.
Inputs: text (required). Returns: tool, result, status, message, +1 more
quick_checkQuick checkARead-onlyIdempotentInspect
Fast, low-cost check of ONE factual claim. Returns verdict supported, contradicted or unsure, a confidence score, a short reason and 1-2 public sources (Wikipedia, plus Wikidata structured facts where they apply) with quote and URL. Synchronous. Cheaper and faster than deep_verify; use it on the claims extract_claims returns (its next_step gives the exact body). Unsure or low-confidence results include a next_step to deep_verify. Price: $0.15 USDC on Base per call via x402; this MCP call returns payment instructions and POST /v1/quick_check returns the verdict. Read-only.
Inputs: claim (required). Returns: tool, result, status, message, +1 more
verify_claimVerify claimARead-onlyIdempotentInspect
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.
Inputs: claim (required), sources, sources_only. Returns: tool, result, status, message, +1 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Statistical adjudication for agents: backtest judges, fact-checks. Pay per call in USDC via x402.
Independent fact-checking for AI answers: a verdict and sources for every claim.
Pay-per-call crypto data for AI agents via x402 -- no API key, no account, no subscription. Pay in USDC per request or try the free tier. TOOLS get_crypto_prices -- free BTC/ETH/SOL prices and 24h change, filter by symbol get_market_quote -- quote for chosen symbols plus market cap and 24h volume get_market_analysis -- AI analysis: sentiment, key levels, risk factors get_research_report -- full technical, on-chain and macro outlook token_safety -- rug-pull risk screening for an EVM token: liquidity, volume, pair age, 0-100 heuristic score from live DEX data fact_check -- verify a claim with an LLM verdict and confidence scrape_url -- fetch any URL and return clean extracted text USE THIS WHEN your agent needs current crypto prices, a market read, an on-chain token safety check, or claim verification, and you would rather pay 0.005-0.25 USDC for the answer than hold a data subscription. Built by Munchausen Lab. Streamable HTTP, 100% uptime over 30 days.
Real-time fact-check, citation verification, and source-freshness for AI agents.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceFacilitates fact-checking claims by searching the web and returning evidence snippets, with pay-per-call via x402 micropayments on Base L2.MIT
- AlicenseNot gradedqualityCmaintenanceReal-time fact-checking agent. Verifies claims and URLs against live web sources. Returns CURRENT, OUTDATED, DISPUTED, or UNVERIFIABLE verdicts with confidence scores and what changed. x402 payments on Base.58 npmMIT
- AlicenseNot gradedqualityBmaintenanceLets AI agents read web pages and batches of URLs with prompt-injection screening, search the web, get cited answers, fact-check claims, and check crypto tokens for scam and rug-pull risk. Each call is paid per use in USDC through x402 (from $0.002), with a spend cap.MIT
- AlicenseAqualityCmaintenanceEnables 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.161 npmMIT
Glama MCP Gateway
Add one secure layer between your agents and this server.