Skip to content

groundcheck MCP server

io.github.beepboop2025/groundcheckbeepboop2025streamable-httpv0.7.2Scanned

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

5 tools: 4 change things and 1 only read.

Tools: 0 delete, 0 irreversible, 4 write, 1 read.
  • Reads private data · 0
  • Reads text others write · 4
  • Can send data out · 0
  • 1 finding

Tools listed without sign-in. Remote posture

With Anlyon

4 tools here change things. Govern them.

  • Anlyon lists the tools and adopts none.
  • Each tool you adopt gets approvals and receipts.
  • Your agent never holds the key.
Govern this server →

A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.

What the groundcheck MCP server can do

The groundcheck MCP server is published by the GitHub account beepboop2025. It has 5 tools. It can create or change data (4 tools: verify_claim, check_citations, extract_claims and attest_delivery), but cannot delete data. 1 tool only reads.

4 tools bring in text other people can write (verify_claim, check_citations, resolve_instrument and 1 more).

The fixed checks matched 1 finding (long-description). Each one comes with the text it matched.

Its remote endpoint lists its tools without sign-in.

Last scanned Nov 17, 2026, version 0.7.2.

Tools

Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.

5 tools

Changes things 4Claude Code: ask
  • attest_deliveryPURPOSE: Neutral delivery verification for agentic commerce.Reads text others write1 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.

    Findings

    • Info

      The description is 2,209 characters long, over the 2,000 this check looks for.

      Matched text

      description ends: "...dict: 'consistent', payment: {bound: true, transaction: '0x…'}, attestation: {…}}"

      What this check looks for
    Description, as the server wrote it
    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: {…}}

    Annotations the server declares

    • title: Attest an x402 delivery
    • readOnlyHint: true
    • idempotentHint: true
    • destructiveHint: false
    • openWorldHint: true
  • check_citationsPURPOSE: 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 o…Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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})

    Annotations the server declares

    • title: Fact-check a whole draft
    • readOnlyHint: true
    • idempotentHint: true
    • destructiveHint: false
    • openWorldHint: true
  • extract_claimsPURPOSE: Split text into independently checkable ATOMIC factual claims — the cheap first step of a verification loop (extract -> ground -> attest).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
    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."]}

    Annotations the server declares

    • title: Extract atomic claims
    • readOnlyHint: true
    • idempotentHint: true
    • destructiveHint: false
    • openWorldHint: false
  • verify_claimPURPOSE: Fact-check one claim against live retrieved sources and return a result you can GATE A DECISION ON, not just read.Reads text others writeNo 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.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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.

    Annotations the server declares

    • title: Verify one claim (free)
    • readOnlyHint: true
    • idempotentHint: true
    • destructiveHint: false
    • openWorldHint: true
Only reads 1Show 1 read-only tool
  • resolve_instrumentPURPOSE: Resolve a security identifier (ticker, ISIN, CUSIP, SEDOL, FIGI) or an instrument name to canonical FIGI records via Bloomberg open symbology (OpenFIGI), WITH provenance a…Reads text others writeNo findings

    Why it is in this group

    • The name "resolve_instrument" says "resolve": a word for reading.

    What it can reach

    • untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
    Description, as the server wrote it
    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', …}]}

    Annotations the server declares

    • title: Resolve a security to FIGI
    • readOnlyHint: true
    • idempotentHint: true
    • destructiveHint: false
    • 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.

Exfil surface

Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.

No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.

Reads private data0
Reads files, mail, messages, databases, secrets, calendars or repositories.
Reads text others write4
Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
Can send data out0
Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.

Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.

Remote posture

What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.

Tools listed without sign-in

Looked at Nov 20, 2026, 19:22 UTC, unchanged since Oct 22, 2026. No credentials were sent and no tool was called. What is looked at.

Reachable
yes
HTTP status of an anonymous initialize
200
tools/list served without credentials
yes
Tools that change things, listed without credentials
4
Protocol version
2025-06-18
WWW-Authenticate on 401
not observed
resource_metadata in WWW-Authenticate
not observed
RFC 9728 protected resource metadata
not observed
Authorization servers
not observed
Legacy HTTP+SSE transport
no
Dynamic client registration
not observed
Client ID metadata documents
not observed
  • WarnThe whole server

    The endpoint served tools/list without credentials, and the list has 4 tools that change things (4 write). Whether a call also works without credentials was not tested: tools are never called.

    Matched text

    https://groundcheck.seiche.info/mcp: tools/list returned 5 tools to an anonymous client, including verify_claim (write), check_citations (write), extract_claims (write), attest_delivery (write)

    What this check looks for

Findings

Matches of fixed checks, with the text they matched.

1 info
  • The description is 2,209 characters long, over the 2,000 this check looks for.

    Matched text

    description ends: "...dict: 'consistent', payment: {bound: true, transaction: '0x…'}, attestation: {…}}"

    What this check looks for

History

Changes to its tool definitions and to its remote endpoint, newest first.

No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.

Install

Pinned to version 0.7.2. Values in angle brackets are yours to fill in.

claude mcp add --transport http groundcheck https://groundcheck.seiche.info/mcp
claude mcp add --transport http groundcheck https://groundcheck.seiche.info/mcp

Run in a terminal.

Claude Code permissions

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

.claude/settings.json
{
  "permissions": {
    "allow": [
      "mcp__groundcheck__resolve_instrument"
    ],
    "ask": [
      "mcp__groundcheck__verify_claim",
      "mcp__groundcheck__check_citations",
      "mcp__groundcheck__extract_claims",
      "mcp__groundcheck__attest_delivery"
    ],
    "deny": []
  }
}

Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as groundcheck. Review it before you use it.

Capability tags behind 4 rules
  • mcp__groundcheck__verify_claim untrusted-input
  • mcp__groundcheck__check_citations untrusted-input
  • mcp__groundcheck__resolve_instrument untrusted-input
  • mcp__groundcheck__attest_delivery untrusted-input

Pin

Keep the decision: fail CI when the tools change, follow every change, or show a badge.

Pin in CI

Fail a build when the tools you reviewed are not the tools the server serves today.

curl -s "https://radar.anlyon.com/api/v1/servers/io.github.beepboop2025/groundcheck/verify?hash=ba6eed1f0a2463196f9691aa774e57f90051639355599f965bf19c96aeb4f14d" | jq -e '.changed == false'

Pinned hash ba6eed1f0a24, from Nov 17, 2026, 05:18 UTC.

Watch

Get told when its tools change: a new tool, a new description, a new class.

https://radar.anlyon.com/servers/io.github.beepboop2025/groundcheck/changes.xml

An Atom feed. Works in any feed reader or Slack's RSS app.

Badge

Anlyon Radar badge for io.github.beepboop2025/groundcheck
[![Anlyon Radar](https://radar.anlyon.com/badge/io.github.beepboop2025/groundcheck.svg)](https://radar.anlyon.com/servers/io.github.beepboop2025/groundcheck)

Source: MCP Registry · repository. Synced Oct 21, 2026, 18:23 UTC.

groundcheck MCP server: questions and answers

Answered from the scan above, not from the publisher's description.

Is the groundcheck MCP server safe?

No scan can promise that. What its definitions show: 5 tools, 4 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.

Can the groundcheck MCP server delete data?

No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.

Can the groundcheck MCP server do things that cannot be undone?

No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.

What tools does the groundcheck MCP server have?

5 tools: 4 write, 1 read. verify_claim, check_citations, extract_claims, attest_delivery and resolve_instrument.

Does the groundcheck MCP server need sign-in or OAuth?

Its remote endpoint listed its tools to an anonymous client, without sign-in.

Does the groundcheck MCP server send data to outside services?

None of its tools sends, posts or publishes, or takes a recipient, channel or URL.

Has the groundcheck MCP server changed its tools?

Not since Anlyon Radar started tracking it. Last scanned Nov 17, 2026.