MCP 服务器

librarian

An MCP server that enables LLMs to search, summarize, and retrieve detailed information from Wikipedia across multiple languages. It supports automated fact-checking by allowing models to proactively verify factual claims using Wikipedia's database.

README

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

</div>

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/librarian with your actual paths
The --directory flag ensures uv uses the correct project environment
Use the full path to uv.exe on 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
Common issues:
- ModuleNotFoundError: Ensure you're using the --directory flag and correct paths
- File not found: Use absolute paths for both command and in args
- Virtual 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").