turath-mcp
MCP server that gives AI clients fast, accurate access to turath.io's books and resources, with tools for author biographies, book metadata, full texts, parsed pages, and catalog search over stdio or HTTP.
README
Turath MCP
An MCP (Model Context Protocol) server that gives AI clients fast, accurate access to the books and resources of turath.io — authors, book metadata, parsed pages, full book dumps, and catalog search — over stdio and Streamable HTTP.
Every request is routed through the turath-sdk
package to the turath.io API. The AI handles the natural language; the server
returns the exact data from turath.io, attributed with a source block.
Features
- 🔌 MCP compatible — Claude Desktop, Claude Web, ChatGPT, Cursor, VS Code, and others.
- 🌐 Two transports — stdio for local integrations, Streamable HTTP for remote/hosted.
- 🔍 Five tools — author biographies, book metadata + indexes, full book files, parsed pages, and catalog search with filters.
- 📖 Accurate results — every answer comes from turath.io via
turath-sdk; no LLM in the loop. - 🛡️ Hardened HTTP — host allow-list, per-IP rate limit, body cap, session reaper,
/health. - 🗄️ Offline-friendly cache — turath.io responses cached in memory (and optionally on disk) for 30 days.
Install
# Run the server locally (stdio)
npx -y turath-mcp
Documentation
Detailed docs live under docs/:
- Tools reference — every tool, its schema, response shape, and examples.
- Integrations — Claude Desktop, Claude Web, ChatGPT, Cursor, and others.
- Architecture — internals: transports, API client, caching, HTTP hardening.
- Development — build, test, add a new tool, deploy.
Quick start (stdio)
npx -y turath-mcp
This runs the server over stdio. Use it with Claude Desktop, Cursor, or any other MCP client that supports the stdio transport.
Quick start (HTTP)
npx -y turath-mcp --http
# → "Turath MCP HTTP server listening on http://0.0.0.0:4000/"
Point your MCP client at http://localhost:4000/. The server also exposes
GET /health for status checks. Configure with PORT, HOST, and the
MCP_* variables documented in docs/architecture.md.
Quick start (Docker)
docker compose up --build
# → "Turath MCP HTTP server listening on http://0.0.0.0:4000/"
Requirements
- Node.js 22+ (required by
turath-sdk) - npm, pnpm, or yarn (project is
yarn@1.22.22) - Network access to
api.turath.ioandfiles.turath.io(all five tools are remote calls)
License
MIT — see LICENSE.
Contact
Email: contact@adelpro.us.kg
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.