
Mcp Factcheck
This server validates your MCP code and documentation against the official spec to catch technical inaccuracies before they ship. It exposes four tools: check_mcp_claim for multi-part validation with compound claim decomposition, check_mcp_quick_fact for yes/no verification, search_spec for semantic lookups across specification versions, and list_spec_versions to see what's available. There's also a migrate-mcp-content prompt that walks you through updating content between spec versions (draft, 2025-06-18, 2024-11-05, etc.). Under the hood it uses OpenAI embeddings for semantic search and AI validation with confidence scoring. Reach for this when writing tutorials, maintaining MCP libraries, or migrating to newer spec versions. Requires an OpenAI API key and supports OpenTelemetry tracing to Arize Phoenix for observability.
- GitHub stars
- 3
- tools
- 4
- auth
- Required
- transport
- STDIO
- env var
- 1
- last updated
- Oct 7, 2025
Tools
4 toolsPublic tool metadata for what this MCP can expose to an agent.
check_mcp_claimComprehensive validation of MCP-related content, decomposing compound claims and returning corrected content with confidence scores.
Comprehensive validation of MCP-related content, decomposing compound claims and returning corrected content with confidence scores.
No parameter schema in public metadata yet.
check_mcp_quick_factQuick fact-checking for single MCP claims, returning a concise verdict with explanation.
Quick fact-checking for single MCP claims, returning a concise verdict with explanation.
No parameter schema in public metadata yet.
search_specSearches MCP specifications using semantic similarity and returns the most relevant specification sections.
Searches MCP specifications using semantic similarity and returns the most relevant specification sections.
No parameter schema in public metadata yet.
list_spec_versionsLists available MCP specification versions with version dates and descriptions.
Lists available MCP specification versions with version dates and descriptions.
No parameter schema in public metadata yet.
Sponsors
Configuration
OPENAI_API_KEY*OpenAI API key for embedding generation and content validation
Readme
MCP Fact-Check MCP Server
An MCP Server for validating code or content against the official Model Context Protocol (MCP) specification to ensure technical accuracy and prevent the spread of misinformation.
π¦ View in MCP Registry - Available in the official MCP Registry
π View Project Roadmap - See planned features and development progress
ποΈ Design Documentation - Technical design and implementation details
Overview
The MCP Fact-Check MCP Server helps ensure technical accuracy when coding or writing about MCP by comparing content against official specifications. It uses:
- Semantic search with OpenAI embeddings to find relevant specification sections
- AI-powered validation to detect inaccuracies and suggest corrections
- Compound claim decomposition to validate complex statements with multiple assertions
- Multiple spec versions support (draft, 2025-06-18, 2025-03-26, 2024-11-05)
Features
MCP Tools Exposed
check_mcp_claim- Comprehensive validation of MCP-related content
Details
- Repository
- github.com/carlisia/mcp-factcheck
- Category
- Search & Web Crawling
- Package
ghcr.io/carlisia/mcp-factcheck:v1.0.0- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active