Model Context Protocol

Connect AI directly to 48,000+ classical Islamic books

The official Model Context Protocol (MCP) server for Maktab-e-Hayat. Use compatible MCP clients to search the library and request passages with volume and page citations. Setup guides cover the clients listed below.

Why the QASRA MCP Server

Search the collection and read its sources

The public MCP endpoint lets compatible assistants search and retrieve classical texts from Sunni and Shia collections.

48,000+

Classical books

Search works on Hadith, Tafsir, Fiqh, Aqidah, history, and philosophy from a compatible AI client.

Citations

Volume and page references

Retrieved passages include source references so you can open the cited work and check the text.

Sunni & Shia

Dual-tradition heritage

Browse classical works from both traditions and use the available tradition filters to narrow a search.

Model Context Protocol

Official MCP Server for Maktab-e-Hayat

Live endpoint: https://api.makteb.org/mcp. Free to access from clients that support the endpoint’s MCP transport.

Connect Maktab-e-Hayat to Cline, Roo Code, GitHub Copilot, or a project-level .vscode/mcp.json. Choose your OS for the exact config path:

Configuration file location
~/Library/Application Support/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
%APPDATA%\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
~/.config/Code/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json
Configuration JSON
{ "mcpServers": { "makteb": { "type": "sse", "url": "https://api.makteb.org/mcp" } } }

Instant 1-click install, or add to your workspace .cursor/mcp.json:

1-Click Install in Cursor →
Configuration file location
~/.cursor/mcp.json
%USERPROFILE%\.cursor\mcp.json
~/.cursor/mcp.json
Configuration JSON
{ "mcpServers": { "maktab-e-hayat": { "type": "sse", "url": "https://api.makteb.org/mcp" } } }

Add Maktab-e-Hayat to your Google Antigravity global MCP config. Choose your OS:

Configuration file location
~/.gemini/antigravity/mcp_config.json
Quick create folder
mkdir -p ~/.gemini/antigravity
%USERPROFILE%\.gemini\antigravity\mcp_config.json
Quick create folder (PowerShell)
New-Item -ItemType Directory -Force -Path "$env:USERPROFILE\.gemini\antigravity"
~/.gemini/antigravity/mcp_config.json
Quick create folder
mkdir -p ~/.gemini/antigravity
Configuration JSON
{ "mcpServers": { "makteb": { "url": "https://api.makteb.org/mcp" } } }

For Claude Code (CLI), one command connects instantly:

claude mcp add makteb https://api.makteb.org/mcp

For Claude Desktop, edit claude_desktop_config.json. Choose your OS:

Configuration file location
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
Configuration JSON
{ "mcpServers": { "makteb": { "url": "https://api.makteb.org/mcp" } } }

Connect OpenAI Codex, Custom GPT Actions, or the ChatGPT Agent framework. Set the endpoint environment variable, or import the OpenAPI schema. Choose your OS:

Set endpoint variable
export MAKTEB_MCP_URL="https://api.makteb.org/mcp" # add to ~/.zshrc
[System.Environment]::SetEnvironmentVariable("MAKTEB_MCP_URL", "https://api.makteb.org/mcp", "User")
export MAKTEB_MCP_URL="https://api.makteb.org/mcp" # add to ~/.bashrc
OpenAPI schema (Custom GPT Action)
Server URL: https://api.makteb.org Auth: None · Import under Actions > Import from URL

Connect Moonshot AI / Kimi via a custom MCP connector (no authentication required):

{ "name": "Makteb", "url": "https://api.makteb.org/mcp", "requiresAuth": false }

Connect Gemini CLI over HTTP transport. Choose your OS for the install + connect command:

brew install gemini-cli && gemini mcp add --transport http makteb https://api.makteb.org/mcp
winget install Google.GeminiCLI; gemini mcp add --transport http makteb https://api.makteb.org/mcp
pip install google-genai && gemini mcp add --transport http makteb https://api.makteb.org/mcp

Add to Grok via grok.com/connectors > New Connector > Custom, or via standard MCP tool bindings:

1. Connector Name Makteb
2. MCP Server URL https://api.makteb.org/mcp
https://api.makteb.org/mcp

Direct JSON-RPC 2.0 endpoint for LangChain, LlamaIndex, AutoGen, CrewAI, or custom agents. Choose your OS:

curl -X POST https://api.makteb.org/mcp \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
Invoke-RestMethod -Uri "https://api.makteb.org/mcp" -Method Post -ContentType "application/json" -Body '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
curl -s -X POST https://api.makteb.org/mcp \ -H "Content-Type: application/json" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}' | jq .
Tools Reference

Five Core MCP Tools

When connected, AI agents automatically invoke these tools to answer theological, historical, and textual queries with verifiable citations.

search_catalog Discovery

Searches 48,000+ books and 6,583 scholars across Arabic, English, and Roman transliterations with optional Sunni / Shia tradition filters.

Example: "Find classical commentaries on Sahih al-Bukhari."
read_book_pages Manuscript Reader

Retrieves verified manuscript passages with exact Volume, Page, and Unit numbers. For PDF-only works, returns multi-volume publication details and reading URLs.

Example: "Extract Volume 1, Page 7 of Sahih al-Bukhari."
get_book_metadata Bibliography

Returns book author details, Hijri death year, historical dynasty/empire, category taxonomy, and direct reading links.

Example: "What is the publication history and era of Al-Kafi?"
get_table_of_contents Chapter Tree

Fetches hierarchical sections (Abwaab, Fasl, Kutub) with internal page numbers and text anchors for structured book navigation.

Example: "List the chapter structure of Muwatta Imam Malik."
get_author_details Scholar Directory

Retrieves biographical profiles, death dates (AH), scholarly tradition, and a complete bibliography of books cataloged under the scholar.

Example: "Who was Al-Shaykh Al-Saduq and what are his preserved works?"
API & Research Access

Building with QASRA AI?

We collaborate with research institutions, developers, and educators. Reach out for high-volume endpoints or custom model integration.

Phone

+91 7737378656 · +91 9529175756

Email

support@qasra.org

Email your enquiry

Describe your project, the material or software involved, and any deadline. For integrations, include your platform and expected usage.

Email support@qasra.org

You can also use the contact form on our home page.