Fact Check MCP
Verifies claims with verdicts (supported/disputed/unverifiable), confidence scores, and cited sources by cross-referencing FoundryNet Data Network and web search.
README
Fact Verification MCP
Fact verification for AI agents — give it a claim, get a verdict
(supported / disputed / unverifiable) with a 0-100 confidence and cited
sources. It classifies each claim's domain and cross-references the FoundryNet
Data Network plus a general web search.
Part of the FoundryNet Data Network. Attest your agent's verification results with MINT Protocol. See also: financial-signals-mcp, cyber-intel-mcp, patent-intel-mcp, gov-contracts-mcp, compliance-mcp, brand-intel-mcp, weather-intel-mcp, academic-intel-mcp, oss-intel-mcp, social-intel-mcp.
Live MCP endpoint (Streamable HTTP):
https://fact-check-mcp-production.up.railway.app/mcp
Tools
| Tool | Price | What it does |
|---|---|---|
verify_claim |
$0.02 | Verify a claim → verdict, confidence, cited sources, explanation |
batch_verify |
$0.01/claim (min $0.05) | Verify many claims in one call |
source_check |
$0.01 | Assess a source URL — domain age (RDAP), trust signals, bias indicators |
daily_brief |
$5 | Curated daily brief — top disputed/most-verified claims, trending topics |
mint_info |
free | FoundryNet Data Network + MINT Protocol |
Free tier: 10 verifications/day per agent. Then x402: the tool returns an
HTTP-402 with a Solana USDC payment memo — pay it, re-call with the same args plus
payment_tx=<signature>. An Authorization: Bearer fnet_… key bypasses the paywall.
How it works
Each claim is classified by domain and cross-referenced against the most relevant FoundryNet data source and a general web search:
- company claims →
brand-intel-mcp - finance claims →
financial-signals-mcp - patents claims →
patent-intel-mcp - regulation claims →
compliance-mcp
The verdict is synthesized from source agreement and returned with the citations that drove it. Results are cached for 24h (keyed by a normalized-claim hash) and carry a MINT provenance attestation so a buyer can verify the result was produced by this server, unaltered.
The general web-search backend needs a
WEB_SEARCH_API_KEY(Brave Search API). Without it, claims with no FoundryNet corroboration returnunverifiablewith a note rather than a guess.
Sources
On demand: a general web search (Brave Search API) + the FoundryNet Data Network sibling servers (called over their public MCP endpoints). Source-credibility checks use keyless RDAP for domain age. Cached in a standalone Supabase project.
Connect
Smithery: @foundrynet/fact-check · MCP registry: io.github.FoundryNet/fact-check-mcp
{ "mcpServers": { "fact-check": { "url": "https://fact-check-mcp-production.up.railway.app/mcp" } } }
Built by FoundryNet · hello@foundrynet.io
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.