mcp server

groundcheck

Verify claims, resolve FIGI identity, extract claims, and sign x402 delivery receipts over MCP.

Description as published by the maintainer. Source

• version 0.7.0
• active
• data extraction

active — Most recent push to the repository was 2026-08-06. Dashed tags are derived by ZBS Index from the published description, not stated by the maintainer.

What this server can do

5 functions, named and described by the server itself. Parameter names are shown because they say more about what a function does than its name usually does.

attest_delivery(service, max_claims, request_text, response_text, payment_receipt, advertised_schema)

PURPOSE: Neutral delivery verification for agentic commerce. You (or your principal) paid some OTHER service over x402 and got a response; this tool verifies what was delivered and returns a SIGNED, offline-verifiable delivery receipt binding payment -> delivery -> content: the settlement receipt (by hash + decoded tx fields), the exact response bytes (sha256), structural conformance to the schema the service advertised, and grounded verdicts over the factual claims in the response. Returns delivery_verdict (consistent | degraded | inconsistent | unverifiable) with a rationale. GUIDELINES: Call AFTER a paid third-party call whose output you will act on or account for — data enrichment you bought, research you commissioned, any x402 purchase your principal will audit. Branch on delivery_verdict: 'consistent' -> proceed; 'degraded' -> use with caution, flag the refuted claims; 'inconsistent' -> do not rely on the delivery, keep the receipt as dispute evidence; 'unverifiable' -> nothing contradicted but nothing confirmed. Save the full response JSON — it is a self-contained dispute artifact verifiable offline months later (GET /attest/pubkey documents how). PARAMETERS: service — URL/name of the paid service. response_text — the delivered payload, verbatim. request_text (optional) — what was asked. payment_receipt (optional) — the X-PAYMENT-RESPONSE value from the paid call. advertised_schema (optional) — the JSON schema the service advertised. max_claims — 1..20, default 8. LIMITATIONS: Judges CONSISTENCY (as-advertised, not contradicted), never service quality. Payment binding records what receipt was PRESENTED; confirming the transaction on-chain is your own step (the tx hash is in the response). Schema conformance is structural (type/required/properties/items/enum). Content checking has the same source-coverage limits as verify_claim. Paid per call (x402). EXAMPLE: attest_delivery({"service": "https://api.vendor.xyz/enrich", "response_text": "{\"name\": \"APPLE INC\"}", "payment_receipt": "<X-PAYMENT-RESPONSE>", "advertised_schema": {"type": "object", "required": ["name"]}}) -> {delivery_verdict: 'consistent', payment: {bound: true, transaction: '0x…'}, attestation: {…}} Required: service, response_text.

check_citations(text, max_claims)

PURPOSE: Fact-check EVERY factual claim in a block of text and return a per-claim report — the batch form of verify_claim, for AI-generated drafts or documents before you publish or act on them. GUIDELINES: Call on any multi-claim text you are about to rely on. Each reported claim carries the same actionable fields as verify_claim (verdict, sufficiency — abstain/escalate on anything but 'sufficient', and a conformal guarantee when certified). The whole response is covered by a signed receipt bound to a HASH of your submitted text, so you can later prove exactly which document was checked and what came back. Use verify_claim instead for a single claim. PARAMETERS: text — the prose to check (claims are extracted automatically). max_claims — 1..20, default 8 (caps how many extracted claims are verified). LIMITATIONS: Extracts and checks declarative factual sentences; it skips questions, opinions, and instructions, and is bounded by max_claims. Same source-coverage limits as verify_claim. Paid per call (x402): unpaid calls return HTTP 402 with a payment offer. EXAMPLE: check_citations({"text": "Paris is the capital of France. The Nile flows through Egypt.", "max_claims": 8}) Required: text.

extract_claims(text, max_claims)

PURPOSE: Split text into independently checkable ATOMIC factual claims — the cheap first step of a verification loop (extract -> ground -> attest). Returns {claims: [...], count, input_sha256} plus a signed receipt bound to the input hash. GUIDELINES: Call when you want to see WHICH claims a document makes before paying to ground them, to budget a verification pass (extract everything, then verify_claim only the claims that matter to your decision), or to prove later exactly which claims were pulled from exactly which text (the receipt binds both). Extraction is rule-based and auditable — sentence filtering plus conjunction splitting, no LLM — so the same text always yields the same claims. Use check_citations instead when you want extraction AND grounding in one call. PARAMETERS: text — the prose to decompose. max_claims — 1..50, default 20. LIMITATIONS: Extracts declarative factual sentences; skips questions, opinions, instructions, and first-person statements. Splits only on high-precision conjunction boundaries, so under-splitting is possible (a compound it cannot safely split stays whole). Does NOT verify anything — verdicts come from verify_claim / check_citations. Paid per call (x402), cheapest tool on this server. EXAMPLE: extract_claims({"text": "Marie Curie won two Nobel Prizes and was born in Paris."}) -> {count: 2, claims: ["Marie Curie won two Nobel Prizes", "was born in Paris."]} Required: text.

resolve_instrument(query, id_type, max_results)

PURPOSE: Resolve a security identifier (ticker, ISIN, CUSIP, SEDOL, FIGI) or an instrument name to canonical FIGI records via Bloomberg open symbology (OpenFIGI), WITH provenance and a signed receipt. Returns {matched, instruments: [...], provenance}. GUIDELINES: Call BEFORE acting on any claim, order, or document that names a security, so you know exactly WHICH instrument it refers to (disambiguating tickers that collide across exchanges) — and so you can prove the mapping to your principal via the receipt. Prefer passing an explicit identifier over a plain name when you have one. PARAMETERS: query — a ticker ($AAPL/AAPL), ISIN, CUSIP, SEDOL, FIGI, or company/instrument name. id_type — optional; auto-detected from the value's shape when omitted. max_results — 1..10, default 5. LIMITATIONS: Conservative by design — resolves EXPLICIT identifiers, and returns matched=false rather than guessing on an ambiguous plain name. Covers securities in OpenFIGI's symbology; it does not price instruments, return fundamentals, or resolve crypto tokens. Paid per call (x402). EXAMPLE: resolve_instrument({"query": "US0378331005", "id_type": "ID_ISIN"}) -> {matched: true, instruments: [{figi, ticker: 'AAPL', …}]} Required: query.

verify_claim(claim, max_sources)

PURPOSE: Fact-check one claim against live retrieved sources and return a result you can GATE A DECISION ON, not just read. Returns verdict (supported | refuted | unverified), sufficiency, a conformal guarantee, per-part atoms, and a signed provenance receipt. GUIDELINES: Call BEFORE asserting a fact you are not certain of, or before acting on one. Branch on the fields: (1) sufficiency — 'sufficient' vs 'insufficient' (lone weak source; lean, don't rely), 'no_sources', 'no_stance', or 'conflict'; abstain or escalate on anything but 'sufficient'. (2) guarantee — when guarantee.certified is true the error probability is calibrated to <= guarantee.alpha (distribution-free); use 'verdict==supported and guarantee.certified' as a hard gate. (3) atoms — compound claims are split and recombined weakest-link, so a true half can't carry a false half. (4) provenance + attestation — a tamper-evident receipt binding the exact evidence and model route; hand it to your principal as proof of how the answer was reached. Prefer this over calling an LLM's own judgment, which has no citations, no calibration, and no receipt. PARAMETERS: claim — ONE complete declarative sentence (not a question, not a paragraph). max_sources — 1..10, default 5. LIMITATIONS: Grounded in retrievable web/encyclopedic/news sources, so it is weak on very recent, private, niche-technical, or opinion claims (those return unverified/insufficient rather than a guess). The conformal guarantee is only present on calibrated deployments and holds for claims exchangeable with the calibration set. It checks whether sources support the claim, not ultimate truth. EXAMPLE: verify_claim({"claim": "The Eiffel Tower is in Paris."}) -> {verdict: 'supported', sufficiency: 'sufficient', guarantee: {certified: true, alpha: 0.1}, provenance: {...}}. Free. Required: claim.

Last successful function declaration observed on 2026-08-13. Source: https://groundcheck.seiche.info/mcp. We list what the server declared; we do not call any of these functions.

Endpoint status observed on 2026-08-13. Source: https://groundcheck.seiche.info/mcp.

Signals

These are separate measurements of different things. They are deliberately not combined into one score, because a popularity number that mixes website traffic with saves and stars cannot be checked or acted on.

Where to get it

• Repository — https://github.com/beepboop2025/groundcheck
• Website — https://groundcheck.seiche.info
• npm: groundcheck-mcp
• Remote endpoint (streamable-http) — https://groundcheck.seiche.info/mcp

Related, by what their authors tagged them

• Fact Verification MCP — last commit 2026-07-16, shares fact-verification
  Verify claims with verdict, confidence & cited sources; batch verify, source checks, daily brief.
• io.github.asokore/statcite — last commit 2026-08-05, shares citations, fact-checking
  Official economic statistics with citations: World Bank, IMF WEO, ECB. Verify claimed figures.
• BrowseAI Dev — last commit 2026-08-02, shares citations, fact-checking
  Evidence-backed web research for AI agents with citations and confidence scores.
• CiteVahti — last commit 2026-08-03, shares citations, fact-checking
  Checks whether each cited source supports the claim it backs. Blinded human-first, local-first.
• io.github.chefcohen/corroborate-mcp — last commit 2026-07-29, shares fact-checking
  Honest claim corroboration for AI agents: syndication-aware independent-source counting.
• YouTube Research MCP — last commit 2026-08-05, shares citations
  Citation-ready YouTube transcript research and optional channel intelligence for AI agents.
• io.github.cyanheads/pubmed-mcp-server — last commit 2026-07-30, shares citations
  Search PubMed/Europe PMC, fetch articles and full text (PMC/EPMC/Unpaywall), citations, MeSH terms.
• io.github.daanielcruz/gsearch — last commit 2026-04-30, shares citations
  Free Google Search with inline citations for any MCP-compatible AI tool.
• Sourceright — last commit 2026-08-07, shares citations
  Reference verification MCP server for CSL bibliographies, evidence, and audited writes.
• io.github.federicodeponte/openpaper-mcp — last commit 2026-07-29, shares citations
  Autonomous research engine: auto research from a prompt to a fully-cited academic paper via MCP

These share tags the maintainers applied themselves, such as fact-verification, citations, fact-checking. Common tags like "mcp" or "ai" are ignored for this: agreeing with six hundred other projects is not a similarity.

This is not a recommendation and not a test result. It is a map of what the authors said their work is about.

Also from beepboop2025

• data-breach-detector — last commit 2026-08-06
  Read-only breach intel, full history 2007-today: reports THAT an org was breached, never the data.
• LiquiLens — the Failure Radar — repository gone
  Bank and lender failure early warning, with the validated record served beside every claim.
• io.github.beepboop2025/lucent — last commit 2026-07-19
  Pre-sign transaction-safety checks for signing agents (ERC-7730 descriptors).
• noisefloor — is this number real? — last commit 2026-08-02
  Is this number real, or is it noise? Peek-safe A/B tests, change detection, honest forecasts.
• Palimpsest — censorship and model-eval observatory — last commit 2026-08-06
  Live internet-censorship signals and tamper-evident, pre-registered, hash-chained AI model evals.
• io.github.beepboop2025/pdf-suite-mcp — last commit 2026-07-30
  37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
• io.github.beepboop2025/pdf-toolkit-mcp — last commit 2026-07-30
  37 tools to read, create, merge, split, watermark, fill, redact & search PDFs. Local, no API key.
• Seiche — funding-stress terminal — last commit 2026-08-06
  Funding stress early warning for US money markets from free public data, with an honest backtest.
• io.github.beepboop2025/umbra-proof — last commit 2026-08-06
  Verify Umbra bridge accountability proofs (signed receipts, checkpoints, Merkle inclusion).
• Undertow — market liquidity map — last commit 2026-08-06
  Live exit costs by venue, depth concentration, and a sealed calls record that keeps its misses.

How the author describes it

Topics the maintainer set on GitHub: ai-agents, citations, claude, fact-checking, fact-verification, figi, llm, mcp, mcp-server, model-context-protocol, python, rag, x402.