MCP Factcheck

Name: MCP Factcheck
Author: carlisia

by carlisiaversion 1.0.0i★ 3iRuns on your computer

Registry nameio.github.carlisia/mcp-factcheck

Install

Overview

Description from the maker (original English)

An MCP server that validates content against MCP specification using semantic search and AI

PopNx MCP’s three pillars

These three are never merged into one score: opinions, measurements and popularity are different things.

User voiceiNo reviews yetReviews open together with accounts in a later step
Our basic checksi1 of 2 passedChecked from public information; code not scanned yet
UsageiVery new★ 3

What you can do with it

We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.

Connection: Runs on your computer
Transport: stdio
Category: Search & AI memory
You need to fill in: OPENAI_API_KEY

Install

Pick the AI app you use, then copy the settings.

Before you install

Basic checks: 1 of 2 passed
Runs on your computer with your user’s permissions (files, network, apps).
You fill in yourself: OPENAI_API_KEY

You need

DockerDocker installed

Which app do you use?

ClaudeClaude CodeCursorVS CodeChatGPT

Pick your app above. We remember it, so next time the button says “Install in …”.

Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json

{
  "mcpServers": {
    "factcheck": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAI_API_KEY",
        "ghcr.io/carlisia/mcp-factcheck:v1.0.0"
      ],
      "env": {
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

Run this in your terminal

claude mcp add factcheck --env OPENAI_API_KEY=your-value -- docker run -i --rm -e OPENAI_API_KEY ghcr.io/carlisia/mcp-factcheck:v1.0.0

Fill in the empty values before running it.

Open in Cursor

Or copy the settings yourself

Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "factcheck": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAI_API_KEY",
        "ghcr.io/carlisia/mcp-factcheck:v1.0.0"
      ],
      "env": {
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

Open in VS Code

Or copy the settings yourself

Paste into .vscode/mcp.json in your project

{
  "servers": {
    "factcheck": {
      "type": "stdio",
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "OPENAI_API_KEY",
        "ghcr.io/carlisia/mcp-factcheck:v1.0.0"
      ],
      "env": {
        "OPENAI_API_KEY": "your-value"
      }
    }
  }
}

Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.

This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.

Your choice stays on this device in a cookie; no account needed.

Values you fill in

OPENAI_API_KEY required env
OpenAI API key for embedding generation and content validation

These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.

Which apps can use it

Based on how this server connects and on each app’s own docs, checked Nov 10, 2026.

Run on your computer in

Claude Goose LM Studio Msty Studio Cherry Studio Cursor VS Code + GitHub Copilot Visual Studio Windsurf (Devin Desktop)Zed Kiro Cline Continue JetBrains AI Assistant Claude Code Codex CLI Gemini CLI OpenCode nodecode Warp LibreChat Raycast

All apps, with pros and cons →

What it can do

Runs on your computer; the tool list appears in your AI app after you install it.

Basic checksi

We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 11, 2026

✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account carlisia, which owns the repo
! Caution
Still maintained
Code last changed 12 months ago, more than 6 months ago
… Not checked yet
Has a licence
We have not read this repo from GitHub yet
– Not applicable
Endpoint responds
This one runs on your computer; there is no internet endpoint
– Not applicable
Sign-in with OAuth
Runs on your computer and uses local settings instead
… Not checked yet
No hidden instructions in tool descriptions
Runs on your computer; we can only read tool lists from internet endpoints

User reviews

No reviews yet

Compared with others in Search & AI memoryi

More stars than 84% of the other 5867 servers in this category
Published to the registry more recently than 1% of the other 5867 servers in this category
Basic checks equal to or better than 14% of the other 5867 servers in this category

Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.

Common questions

Is MCP Factcheck safe?

It passed 1 of 2 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.

What keys or codes does it need?

You need to fill in: OPENAI_API_KEY

Does it run on my computer or in the cloud?

It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).

Is it still maintained?

The GitHub repo last changed 12 months ago, and the latest version (1.0.0) reached the registry 13 months ago.

Which apps can use it?

Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.

What can I use instead?

In the same category: Ruflo, Context7, Metabase

Alternatives

Servers in the same category from other makers, sorted by stars.

Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi

Ruflo

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

by ruvnetWidely used↓ 74.3K/wk★ 81.4KUpdated today

Runs on your computer

Install

Context7

Feeds AI the latest docs for libraries and frameworks before it answers, so code it writes does not use outdated, removed functions.

by upstashWidely used↓ 1.2M/wk★ 64.4KUpdated yesterday

Computer or cloud

Install

Metabase

Lets AI clients search, explore, query, and visualize data in a Metabase instance.

by metabaseWidely used★ 50.3KUpdated 6 months ago

Runs in the cloud

Install

README from the maker

Open the README

Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.

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.

📦 [View in MCP Registry](https://registry.modelcontextprotocol.io/?q=mcp-factcheck) - Available in the official MCP Registry

📋 [View Project Roadmap](ROADMAP.md) - See planned features and development progress

🏗️ [Design Documentation](DESIGN.md) - 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

Validates multi-claim content (documentation, tutorials, bullet points)
Automatically decomposes compound claims (e.g., "X and Y") for accurate validation
Provides step-by-step validation workflow
Identifies missing best practices and modal verb issues
Returns corrected content with confidence scores

`check_mcp_quick_fact` - Quick fact-checking for single MCP claims

Validates single sentences or quick questions
Returns concise ✓/✗ verdict with explanation
Uses aggressive search strategies for accuracy
Perfect for "Does MCP support X?" questions

`search_spec` - Searches MCP specifications using semantic similarity

Returns most relevant specification sections
Supports all specification versions

`list_spec_versions` - Lists available MCP specification versions

Shows version dates and descriptions
Indicates which version is current

MCP Prompts Available

`migrate-mcp-content` - Guides content migration between MCP specification versions

Validates content against source specification first
Identifies changes between specification versions
Provides step-by-step migration guidance
Works with any type of MCP-related content
Preserves the original tone, style, and voice when making corrections or suggestions

Parameters:

current_version (required): Source MCP specification version (e.g., "2024-11-05", "2025-06-18")
target_version (required): Target MCP specification version to migrate to (e.g., "draft")
update_scope (optional): Determines how aggressive the migration should be
critical_only: Fix only critical inaccuracies and breaking changes (minimal changes)
enhancement_focused: Fix issues and improve clarity, align with best practices
comprehensive: Complete review with all improvements and enhanced clarity
Default: comprehensive

Installation

The MCP Fact-Check server is available through the Model Context Protocol registry. Install it directly from your MCP client:

For Claude Desktop and other MCP clients:

Search for "mcp-factcheck" in your client's server marketplace
Click install
Provide your OpenAI API key when prompted

That's it! The server will be automatically configured and ready to use.

For developers: If you need to build from source or contribute to the project, see INSTALL.md for development setup instructions.

Observability

Visual Tracing with Arize Phoenix

For a beautiful, AI-focused trace visualization UI, set up Arize Phoenix:

Install and start Phoenix:

# Install Phoenix

pipx install arize-phoenix

Start Phoenix server

phoenix serve

Update the Host config to send traces to Phoenix:

"mcpServers": { "mcp-factcheck": { "command": "/path/to/bin/mcp-factcheck-server", "args": [ "--data-dir", "/path/to/data/embeddings", "--telemetry", "--otlp-endpoint", "http://localhost:6006" ], "env": { "OPENAI_API_KEY": "your-api-key" } } } }

View traces at: http://localhost:6006

What you'll see in Phoenix:

Beautiful AI-focused interface designed for LLM applications
Complete validation pipeline timeline with clear visual hierarchy
Embedding generation performance and OpenAI API call tracking
Vector search visualization with similarity scores
Per-chunk validation confidence levels and quality metrics
Cost tracking for OpenAI API usage (or whichever llm is being used for embedding the input content/code)
Clean, intuitive navigation focused on AI workflows

Phoenix is specifically designed for AI/ML observability and provides a much more user-friendly experience than traditional tracing tools.

Development

Building

# Build all components

go build -o bin/mfc ./cmd/server go build -o bin/specloader ./utils/cmd

Run tests

go test ./...

Updating Specifications

The project includes pre-extracted MCP specifications and embeddings for all versions. To check when the draft specification was last updated, see data/SPEC_METADATA.json:

# View draft update information

cat data/SPEC_METADATA.json | jq '.specs.draft'

To update the draft specification:

./bin/specloader spec --version draft

./bin/specloader embed --version draft ./bin/specloader embed --version draft-fine

To add a new specification version:

./bin/specloader spec --version 2025-12-15

./bin/specloader embed --version 2025-12-15 ./bin/specloader embed --version 2025-12-15-fine

All specification extraction dates and source commits are automatically tracked in data/SPEC_METADATA.json.

Testing Tools

Test the server using the included test client:

# Build test client

go build -o bin/factcheck-curl ./cmd/factcheck-curl

Test tools

./bin/factcheck-curl --cmd ./bin/mfc --data-dir ./data/embeddings tools/list ./bin/factcheck-curl --cmd ./bin/mfc --data-dir ./data/embeddings tools/call validate_content '{"content":"MCP is a protocol"}'

Test prompts

./bin/factcheck-curl --cmd ./bin/mfc --data-dir ./data/embeddings prompts/list

Get migration prompt with minimal parameters

./bin/factcheck-curl --cmd ./bin/mfc --data-dir ./data/embeddings prompts/get migrate-mcp-content '{"current_version":"2024-11-05","target_version":"draft"}'

Get migration prompt with all parameters

./bin/factcheck-curl --cmd ./bin/mfc --data-dir ./data/embeddings prompts/get migrate-mcp-content '{ "current_version": "2024-11-05", "target_version": "2025-06-18", "update_scope": "critical_only" }'

Architecture

See DESIGN.md for the complete architecture documentation.

Environment Variables

OPENAI_API_KEY - Required for embedding generation and content validation
GITHUB_TOKEN - Optional, for higher GitHub API rate limits when extracting specs

License

MIT License. See LICENSE for details.

MCP Factcheck

Overview

PopNx MCP’s three pillars

What you can do with it

Install

Before you install

Values you fill in

Which apps can use it

Related guides

What it can do

Basic checksi

Maker matches the repo

Still maintained

Has a licence

Endpoint responds

Sign-in with OAuth

No hidden instructions in tool descriptions

User reviews

Compared with others in Search & AI memoryi

Common questions

Alternatives

Ruflo

Context7

Metabase

README from the maker

MCP Fact-Check MCP Server

Overview

Features

MCP Tools Exposed

MCP Prompts Available

Installation

Observability

Visual Tracing with Arize Phoenix

Start Phoenix server

Development

Building

Run tests

Updating Specifications

Testing Tools

Test tools

Test prompts

Get migration prompt with minimal parameters

Get migration prompt with all parameters

Architecture

Environment Variables

License