# Claim Grounding

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

- name: io.github.truepointmarketingpartners-dotcom/claim-grounding
- version: 1.4.7
- connection class: R0 (autonomous)
- trust: 97/100
- quality: 91/100 (strong)
- owner: not claimed
- descriptor: https://api.protogrid.dev/v1/servers/io.github.truepointmarketingpartners-dotcom%2Fclaim-grounding
- tools: https://api.protogrid.dev/v1/servers/io.github.truepointmarketingpartners-dotcom%2Fclaim-grounding/tools

**An agent can connect right now, no human step.** Remote endpoint, no authentication, reachable on the last probe.

## Connection (mcpServers)

```json
{
  "mcpServers": {
    "claim-grounding": {
      "type": "http",
      "url": "https://claim-grounding.prospectintel.workers.dev/mcp"
    }
  }
}
```


## Trust

- hygiene: 100
- liveness: 99
- freshness: 100
- provenance: 90
- drivers: +repository +namespace-matches-repo +website +reachable +uptime-97% +updated-5d-ago
- Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed.

## Quality 91/100 (strong)

### protocol: 75 (weight 25)

- warn `protocol.modern`: newest supported version is 2025-11-25; 2026-07-28 not supported, older versions are deprecated until 2027-07-28
- n/a `protocol.stateless`: only applies to 2026-07-28 servers
- pass `protocol.transport`: streamable HTTP
- n/a `protocol.list_ttl`: only applies to 2026-07-28 servers

### authorization: n/a (weight 15)

- n/a `auth.prm`, `auth.as_metadata`, `auth.cimd`: no remote uses OAuth
- n/a `auth.secret_in_url`: no templated URL

### tool hygiene: 100 (weight 30)

- pass `tools.descriptions`: every tool has a description
- pass `tools.description_length`: descriptions are concise
- pass `tools.schemas`: every tool has an object input schema
- pass `tools.annotations`: 4 of 4 tools declare readOnlyHint or destructiveHint
- pass `tools.directory_hints`: every tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
- pass `tools.token_cost`: about 1,944 tokens to load every tool
- pass `tools.api_dump`: tools are not a one-to-one API dump

### stability: 100 (weight 15)

- pass `stability.changes`: 5 tool changes in 30 days
- pass `stability.rug_pull`: no tool changed its meaning under the same name

### dependencies: n/a (weight 15)

- n/a `deps.known_vulns`, `deps.mcp_sdk_version`, `deps.resolvable`: no npm or PyPI package

- tools: 4, about 1,944 tokens to load them all
- tool set hash: 9f576ddadd1d5d8c01334acd13bb8c57
- tools last changed: 2026-10-14T19:58:20.282Z
- badge: [![protogrid quality](https://protogrid.dev/badge/io.github.truepointmarketingpartners-dotcom/claim-grounding.svg)](https://protogrid.dev/servers/io.github.truepointmarketingpartners-dotcom/claim-grounding)
- Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed.

### Tool changes

- 2026-10-14 `check_answer` changed (description, outputSchema)
  - before: Fact-check a whole answer: extracts every checkable claim and verifies each one against public Wikipedia sources, returning a verdict, confidence, quote and source URL per claim plus suggested next actions. Use it to audit chatbot or RAG output before showing it to a user. Price: $1.00 USDC on Base per call via x402; this MCP call returns payment instructions and the paid HTTP route POST /v1/check_answer returns the per-claim results. Read-only.
  - after: 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.
- 2026-10-14 `extract_claims` changed (description, outputSchema)
  - before: Split a text (for example an AI-generated answer) into atomic factual claims, each with its character span and a grounding_required flag that says whether it is a checkable fact (questions, greetings and opinions are flagged false). Use it before verify_claim to decide what to check. Price: $0.05 USDC on Base per call via x402; this MCP call returns payment instructions and the paid HTTP route POST /v1/extract_claims returns the claims. Read-only, no side effects.
  - after: 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.
- 2026-10-13 `deep_verify` changed (inputSchema)
- 2026-10-13 `check_answer` changed (inputSchema, outputSchema)
- 2026-10-13 `verify_claim` changed (inputSchema, outputSchema)

Full history: https://api.protogrid.dev/v1/servers/io.github.truepointmarketingpartners-dotcom%2Fclaim-grounding/changes

## Remotes

- https://claim-grounding.prospectintel.workers.dev/mcp (streamable-http, auth none, reachable true, uptime30d 0.9677419)

## Packages

_none_

## Tools (4)

- `check_answer`: 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.
- `deep_verify`: Multi-source verification of up to three claims in a text against Wikipedia, Wikidata, Google News, Europe PMC (PubMed studies), FRED (US economic data) and SEC EDGAR (US company filings). Returns verdict, confidence, evidence for and against with quotes and URLs, and flags contradiction when sources disagree. Async: the paid call returns a job_id; poll GET /v1/jobs/{job_id} for free until status is succeeded. Price: $0.75 USDC on Base per call via x402; this MCP call returns payment instructions for POST /v1/deep_verify. Read-only. Not legal, medical or compliance advice.
- `extract_claims`: 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.
- `verify_claim`: 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.