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 Turath for books about Islamic history"
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
An MCP (Model Context Protocol) server for turath.io — search the Islamic library, read book pages, and look up books, authors and categories from Claude or any MCP client.
No download or build needed. Requires Node.js 18+.
Quick start
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"turath": {
"command": "npx",
"args": ["-y", "github:achrafmontage/turath-mcp"]
}
}
}Claude Code
claude mcp add turath -- npx -y github:achrafmontage/turath-mcpCursor / other clients
Use the same command: npx -y github:achrafmontage/turath-mcp
Once published to npm, replace
github:achrafmontage/turath-mcpwithturath-mcp.
Related MCP server: turath
Tools
Tool | Description |
| Full-text search across the library |
| Text of one book page |
| Up to 10 consecutive pages |
| Book metadata and table of contents |
| Author details |
| Book categories |
| Find book/author/category IDs by name |
| One category with its books (paged) |
| Static JSON of a whole book (asks for confirmation via elicitation) |
| Summarize a page with the client model (sampling) |
| Save pages as .md inside the client's root folder (roots) |
| Fetch up to 100 pages as a background task (tasks) |
Resources: turath://categories, turath://category/{id}, turath://book/{id}, turath://book/{id}/page/{page}
Prompts: research_topic, explore_category (with argument completion)
MCP capabilities
Server: tools, resources, prompts, logging, completions, tasks (experimental), experimental (turath/arabic-normalization).
Client features used when available: roots, sampling, elicitation (each tool degrades with a clear message if the client lacks it).
Development
npm install
npm run build
npm run inspect # opens MCP Inspectorbuild/ is committed so npx github:... works instantly; run npm run build before committing source changes.
Disclaimer
Unofficial project, not affiliated with turath.io. Content belongs to its respective owners; please respect turath.io's terms of use.
License
MIT
Available Tools
12 toolsturath_export_pagesExport pages to a markdown fileB
Saves a page range as a .md file in a turath-exports folder: inside the client root if shared, otherwise TURATH_EXPORT_DIR, otherwise the home directory.
Inputs: book_id (required), to_page (required), from_page (required).
turath_fetch_pages_taskFetch many pages (task)A
Fetches up to 100 consecutive pages as a background task; poll with tasks/get and read with tasks/result.
Inputs: book_id (required), to_page (required), from_page (required).
turath_find_in_catalogFind books, authors or categories by nameBRead-only
Search the Turath catalog (data-v3.json) by name; Arabic diacritics and letter variants are ignored.
Inputs: kind (required), query (required), limit.
turath_get_authorGet author detailsARead-only
Author details: name, death year and the ids of their books (from the Turath catalog), merged with live details from the author API when available.
Inputs: author_id (required), limit, offset, include_books.
turath_get_bookGet book infoCRead-only
Book metadata, optionally with its table of contents (indexes).
Inputs: book_id (required), include_indexes.
turath_get_book_fileGet static book fileARead-only
Fetch the static JSON of a whole book (large). Asks for confirmation if the client supports elicitation. Output is truncated.
Inputs: book_id (required).
turath_get_categoryGet category by IDARead-only
One category with its books. Books are paged; use offset/limit to walk large categories.
Inputs: category_id (required), limit, offset, include_books.
turath_get_pageGet book pageBRead-only
Fetch the text of one page of a book.
Inputs: page (required), book_id (required).
turath_get_pagesGet a range of pagesARead-only
Fetch up to 10 consecutive pages of a book in one call.
Inputs: book_id (required), to_page (required), from_page (required).
turath_list_categoriesList categoriesARead-only
List all Turath book categories (id, name, number of books). Use turath_get_category for one category.
Inputs: no named parameters.
turath_searchSearch TurathBRead-only
Full-text search across the Turath Islamic library. Arabic queries work best.
Inputs: query (required), page, precision.
turath_summarize_pageSummarize a book page (uses client sampling)ARead-only
Fetches a page and asks the client's own model to summarize it. Requires a client with sampling support.
Inputs: page (required), book_id (required), language.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 12 tools
Most tools target distinct resources (search, book, author, category, catalog, export), but the page-fetching family — turath_get_page, turath_get_pages, turath_fetch_pages_task, and turath_get_book_file — overlaps in purpose and is differentiated only by size/mechanism. turath_search (full-text) vs turath_find_in_catalog (catalog name search) could also be briefly confused, though the descriptions do draw the line.
All twelve tools follow a turath_ prefix with snake_case verb_noun structure (get_page, list_categories, export_pages), which is highly predictable. Minor deviation: get vs fetch verbs are mixed for page retrieval (turath_get_pages vs turath_fetch_pages_task), but the pattern remains readable.
Twelve tools is well within the ideal 3-15 range for a library server. Each tool earns its place: search, browsing hierarchy (categories → category → book → author), page retrieval at three scales, plus summarize/export/task utilities.
The read-only domain is well covered: search, category listing and drill-down, book metadata/TOC, author details, page retrieval at multiple granularities, plus export and summarization. Minor gaps: no dedicated author listing/browse tool (only catalog name search) and no way to navigate pages relative to a search hit, but agents can work around these.
Maintenance
Related MCP Connectors
Access Sefaria's library of Jewish texts, commentaries, and learning schedules via MCP
Agentic AI book creator: plan, write, illustrate, narrate, and publish books from any MCP client.
Read-only MCP server exposing a user ORANO library to their own AI agent.
Query your own PDFs and documents from any MCP client. Every answer cites the page it came from.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables fetching and searching canonical hadith texts (Arabic and English) with cross-references and citation-safe URLs for assistants, built on FastMCP.3GPL 3.0
- 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.MIT
- AlicenseAqualityCmaintenanceEnables browsing, searching, and quote verification of a local ebook library via MCP, providing deterministic RAG with no embeddings or network.62MIT
- AlicenseNot gradedqualityDmaintenanceProvides AI clients with fast, hallucination-free access to the Quran through 13 MCP tools, covering search, navigation, morphology, tafsir, translations, and surah background over stdio and Streamable HTTP.MIT