turath-mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@turath-mcp search for books by Ibn Taymiyyah"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
turath-mcp
MCP server for turath.io — access thousands of classical Arabic and Islamic books via the Model Context Protocol.
Built on the public turath.io API, maintained by Nuqayah.
Features
8,500+ books — classical Islamic texts: tafsir, hadith, fiqh, usul, Arabic language, biography, history, and more
No API key required — zero configuration, works out of the box
Full-text search — search across the entire catalog by keyword, author, category, or century
Page-level reading — retrieve any page from any book as plain text (with chapter headings)
Chapter navigation — every book includes a complete index of chapters with page numbers
Author biographies — comprehensive metadata including full name, death year, and biographical notes
Related MCP server: Islamic Content MCP Server
Tools
turath_get_book_info
Get book metadata, chapter index, and page map.
Parameter | Required | Description |
| ✅ | Turath.io book ID (e.g., |
Example:
turath_get_book_info({ book_id: 9953 })turath_get_page
Get the text content of a specific page.
Parameter | Required | Description |
| ✅ | Turath.io book ID |
| ✅ | Printed page number to retrieve |
Example:
turath_get_page({ book_id: 9953, page: 20 })turath_search
Search books in the turath.io catalog by keyword.
Parameter | Required | Description |
| ✅ | Search keyword(s) in Arabic or English |
| ❌ | Filter by category ID |
| ❌ | Filter by author ID |
| ❌ | Restrict search to a specific book ID |
| ❌ | Paginate results (page number) |
Example:
turath_search({ query: "الرسالة" })turath_get_author
Get author biography and metadata.
Parameter | Required | Description |
| ✅ | Turath.io author ID (e.g., |
Example:
turath_get_author({ author_id: 125 })turath_get_book_file
Get full book JSON dump. Only available for books that have a JSON file on the CDN.
Parameter | Required | Description |
| ✅ | Turath.io book ID |
Requirements
Node.js >= 22
An MCP-compatible client (OpenCode, Claude Code, Copilot, etc.)
Installation
Option 1: Clone & run
git clone https://github.com/opin22/turath-mcp
cd turath-mcp
npm install
npm startOption 2: Use with OpenCode
Add to your opencode.json:
{
"mcp": {
"turath-mcp": {
"type": "local",
"command": ["npx", "--yes", "tsx", "/path/to/turath-mcp/src/index.ts"]
}
}
}Option 3: Use with Claude Code / other MCP clients
Configure it in your MCP settings file:
{
"mcpServers": {
"turath-mcp": {
"command": "npx",
"args": ["--yes", "tsx", "/path/to/turath-mcp/src/index.ts"]
}
}
}How to find book IDs
Go to app.turath.io
Search for a book
Open a book and look at the URL:
https://app.turath.io/book/9953The number (
9953) is the book ID
Alternatively, use turath_search to find books by name and get their IDs from the results.
Ethics & Rate Limiting
This server wraps a public, free API. Please be respectful:
Avoid hammering the API with concurrent requests
Cache results when possible
If you build something that generates significant traffic, consider self-hosting
Data Source
All content is served from turath.io, a project by Nuqayah. The books are digitized classical Islamic texts — the vast majority are public domain.
License
MIT
Available Tools
5 toolsturath_get_authorB
Get author biography and metadata from turath.io
Inputs: author_id (required).
turath_get_book_fileB
Get full book JSON dump (may not be available for all books)
Inputs: book_id (required).
turath_get_book_infoA
Get book metadata, chapter index, and page map from turath.io
Inputs: book_id (required).
turath_get_pageB
Get the text content of a specific page from a book
Inputs: page (required), book_id (required).
turath_searchC
Search books on turath.io catalog by keyword
Inputs: query (required), book, page, author, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 5 tools
Each tool targets a distinct aspect of the domain (author, book file, book info, page content, catalog search) with no functional overlap.
Four tools use a consistent 'turath_get_' pattern, but 'turath_search' deviates by omitting the 'get_' prefix, causing a minor inconsistency.
Five tools is well-scoped for a cultural heritage book server, covering core read operations without being too few or excessive.
The set covers essential read operations (search, book info, page content, author info, full file dump), though a browse or list tool could be a minor addition.
Maintenance
Related MCP Connectors
Quran: Quran API Service with 90+ different languages and 400+ translations.
Classical Islamic library (Shamela, 8,594 books): verbatim Arabic cited by volume and page. No key.
Search and retrieve Quran ayahs, tafsir commentary, hadith, and detailed hadith records.
Quran, hadith collections and tafsirs: browse books and chapters, read verses, full-text search
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides AI assistants with comprehensive access to Islamic resources including Quran verses with translations, Tafsir commentary, Hadith collections, and audio recitations. Enables users to explore Islamic texts, get daily inspiration, and access scholarly interpretations through natural language queries.1830 npm10MIT
- AlicenseAqualityBmaintenanceConnects AI assistants to authentic Islamic content including Qur'an, Hadith, and resources in multiple languages via over 80 tools.745 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP server to search and retrieve passages from a corpus of 7,872 classical Islamic books via the Sahifah API, with full citations and mu'tabar filtering.21 npmMIT
- AlicenseNot gradedqualityDmaintenanceMCP 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.21 npm1MIT