Librarian

git clone <your-repository-url> cd librarian uv sync

The server starts onhttp://0.0.0.0:8000. The MCP endpoint is available at/mcp.

For production deployments behind gunicorn, use the ASGI adapter:

gunicorn librarian_wsgi:app -w 4 -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:8000

Add this to your MCP client configuration to connect to the server:

{ "mcpServers": { "librarian": { "url": "https://your-server-host/mcp" } } }

claude mcp add librarian -t http http://localhost:8000/mcp

The Wikipedia tools will be available automatically in your next Claude Code session.

To make your LLM client 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 prompt by referencing:fact_checking_instructions

Once configured, your LLM client 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
- 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").

Screenshot showing the Wikipedia tools available when the MCP server is properly configured

MCP client showing the librarian server successfully connected and available

Example of using the librarian tools within VS Code with GitHub Copilot

This project was originally built against the MCP2025-11-05spec (SDK v1.x). It has been fully migrated to theMCP2026-07-28spec(SDK v2.0.0).

The 2026-07-28 release is the most significant MCP revision to date. Its core change is a shift from astateful, session-basedprotocol to astateless, request/responseprotocol:

- Theinitialize/initializedhandshake isremoved— clients send capabilities on every request via_meta
- TheMcp-Session-Idheader isremoved— servers are now load-balancer friendly out of the box
- TheWebSocket transport is removedentirely
- TheHTTP+SSE transport is deprecatedin favour of Streamable HTTP
- A newserver/discoverendpoint is required (handled automatically by the SDK)
- Tool/resource/prompt results are nowvalidated against the protocol schema at decoration time

The previous WebSocket (wss://) and SSE (/sse) endpoints are no longer available. All clients connect via the Streamable HTTP endpoint:

{ "mcpServers": { "librarian": { "url": "https://your-server-host/mcp" } } }

This project is open source. Please check the license file for details.

Search global news using natural language. Webz.io News Search API returns the most relevant articles and content, with filters for source, country, language, date, sentiment, and category.

Structural AI Search Readiness MCP. Audit, dry-run fixes, rescore, doctor. No LLM rankings.

Efficient web search optimized for LLM-friendly content using the Jina AI API.

A comprehensive, production-ready research server (MCP). Provide your LLM clients with real-time access to the web, data, and more.

Provides web search functionality powered by the Claude API from Anthropic.

Connect Claude, ChatGPT, Grok or Cursor to 27.6 crore Indian court case records, orders, judgments and cause lists.

e-Gov法令API v2 をラップした Model Context Protocol (MCP) サーバーです。日本の法令データ（法令一覧・改正履歴・法令本文・添付ファイルなど）をMCP対応クライアント（Claude Codeなど）から検索・取得できるようにします。

Fetches user data and event information from the Connpass platform using the Connpass and Gemini APIs.

good-honker is a free conversational front end to the band Goose's show history, usable from Claude. Ask in plain English about setlists, jam charts, venue stats, song history, and upcoming shows. Every answer is fetched live from the open ElGoose.net API and credited to ElGoose; nothing is stored.

good-wook is a free conversational front end to Phish's show history, usable from Claude. Ask in plain English about setlists, song gaps and history, jam charts, venue stats, and upcoming shows. Every answer is fetched live from the Phish.net API and credited to Phish.net; nothing is scraped or stored.