Librarian
A server to query Wikipedia and automatically fact-check information for any LLM with a compatible MCP client.
librarian
Librarian is a MCP (Model Context Protocol) Server that allows any LLM with a compatible MCP client to query Wikipedia for information. It can be configured to automatically fact-check information without requiring explicit user requests.
Note: While this guide focuses on Claude Desktop setup, Librarian also supports remote hosting via WebSocket/HTTP for broader accessibility.
"The only thing that you absolutely have to know is the location of the library."
— Albert Einstein
Example of Claude Desktop using the librarian MCP server to fact-check information
Features
- Automatic Fact-Checking: Configure Claude Desktop to proactively verify factual claims using Wikipedia
- Wikipedia Search: Search for relevant Wikipedia articles
- Page Information: Get detailed information about specific Wikipedia pages
- Page Summaries: Quick summaries of Wikipedia pages
- Page Sections: Get specific sections from Wikipedia pages
- Multi-language Support: Query Wikipedia in different languages
Installation
Claude Desktop Setup
1. Prerequisites
- Claude Desktop installed on your computer
- uv package manager installed
- Python 3.13 or higher
2. Clone and Set Up the Project
git clone <your-repository-url>
cd librarian
uv sync
3. Configure Claude Desktop
Add this configuration to your Claude Desktop configuration file:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
For Windows:
{
"mcpServers": {
"librarian": {
"command": "C:\\Users\\[USERNAME]\\.local\\bin\\uv.exe",
"args": ["--directory", "C:\\Users\\[USERNAME]\\path\\to\\librarian", "run", "python", "librarian_stdio.py"],
"env": {
"PYTHONPATH": "C:\\Users\\[USERNAME]\\path\\to\\librarian"
}
}
}
}
For macOS/Linux:
{
"mcpServers": {
"librarian": {
"command": "uv",
"args": ["--directory", "/path/to/your/librarian", "run", "python", "librarian_stdio.py"],
"env": {
"PYTHONPATH": "/path/to/your/librarian"
}
}
}
}
Important:
- Replace
[USERNAME]and/path/to/your/librarianwith your actual paths - The
--directoryflag ensures uv uses the correct project environment - Use the full path to
uv.exeon Windows for reliability
4. Restart Claude Desktop
After adding the configuration, restart Claude Desktop completely to load the MCP server.
5. Troubleshooting
If you encounter issues:
-
Check Claude Desktop logs:
- Windows:
%AppData%\Claude\logs\mcp-server-librarian.log - macOS:
~/Library/Logs/Claude/mcp-server-librarian.log
- Windows:
-
Common issues:
ModuleNotFoundError: Ensure you're using the--directoryflag and correct pathsFile not found: Use absolute paths for bothcommandand inargsVirtual environment warnings: These are harmless but can be avoided with proper paths
-
Test manually:
cd /path/to/librarian uv run python librarian_stdio.py # Should start without errors
Automatic Fact-Checking Setup
To make Claude Desktop automatically use Wikipedia for fact-checking, start your conversations with:
"Use your Wikipedia tools to automatically fact-check any factual claims in our conversation. Don't wait for me to ask - proactively verify information and provide corrections when needed."
Or use the built-in system prompt by referencing: fact_checking_instructions
Behavior Examples
Once configured, Claude Desktop will automatically:
- ✅ Verify historical dates and events
- ✅ Check biographical information
- ✅ Confirm scientific facts and discoveries
- ✅ Validate geographical information
- ✅ Correct common misconceptions
- ✅ Provide source attribution from Wikipedia
Available Tools
- search_wikipedia_pages: Search for Wikipedia articles on any topic and return the top 5 results with selection information
- get_wikipedia_page_info: Get comprehensive information about a specific page including content, summary, hyperlinked words, and categories
- get_wikipedia_page_summary: Get quick summaries of Wikipedia pages with customizable sentence length
- get_wikipedia_page_sections: Get a list of all sections on a Wikipedia page for large pages where you need specific information
- get_wikipedia_page_sections_info: Get detailed content for specific sections of a Wikipedia page by title or index
All tools support multi-language Wikipedia queries by specifying the language parameter (default: "en").
Examples
Available Tools in Claude Desktop
Screenshot showing the Wikipedia tools available in Claude Desktop when the MCP server is properly configured
MCP Servers Configuration
Claude Desktop showing the librarian MCP server successfully connected and available
VS Code Integration Example
Example of using the librarian tools within VS Code with GitHub Copilot
License
This project is open source. Please check the license file for details.
Serveurs connexes
domain-search-mcp
Domain Search MCP is an open-source MCP server that gives AI assistants the ability to check domain availability in real-time.
Lancelot-MCP
A containerized MCP server for LanceDB vector search, featuring hybrid processing with Gemini and Ollama.
Drawing Guides
Access step-by-step drawing tutorials and guides from easydrawingguides.com for artists of all skill levels.
Crawleo MCP Server
Crawleo MCP - Web Search & Crawl for AI Enable AI assistants to access real-time web data through native tool integration. Two Powerful Tools: web.search - Real-time web search with flexible formatting Search from any country/language Device-specific results (desktop, mobile, tablet) Multiple output formats: Enhanced HTML (AI-optimized, clean) Raw HTML (original source) Markdown (formatted text) Plain Text (pure content) Auto-crawl option for full content extraction Multi-page search support web.crawl - Deep content extraction Extract clean content from any URL JavaScript rendering support Markdown conversion Screenshot capture Multi-URL support Features: ✅ Zero data retention (complete privacy) ✅ Real-time, not cached results ✅ AI-optimized with Enhanced HTML mode ✅ Global coverage (any country/language) ✅ Device-specific search (mobile/desktop/tablet) ✅ Flexible output formats (4 options) ✅ Cost-effective (5-10x cheaper than competitors) ✅ Simple Claude Desktop integration Perfect for: Research, content analysis, data extraction, AI agents, RAG pipelines, multi-device testing
Academic Paper Search
Search and retrieve academic paper information from multiple sources like Semantic Scholar and CrossRef.
Mevzuat MCP
Provides programmatic access to the Turkish Ministry of Justice Legislation Information System (mevzuat.gov.tr) for searching and retrieving legal texts.
IACR ePrint Archive
Search and retrieve cryptographic research papers from the IACR Cryptology ePrint Archive.
Google Maps
An MCP server for interacting with the Google Maps API, designed for Google Cloud Run.
IndieStack
Search and discover 130+ curated indie SaaS tools from your AI coding assistant
BGPT MCP API
Search scientific papers from any MCP tool. Raw experimental data from full-text papers — methods, results, quality scores. 50 free searches, then $0.01/result.