mcpField
Q
quran-search-engine-mcp

quran-search-engine-mcp

Local
github.com/adelproSearch6Updated 12w ago

About quran-search-engine-mcp

quran-search-engine-mcp is an MCP server for AI clients that need exact Quran text and related lookup. It uses a dedicated search engine and verified dataset rather than generating verses with an LLM.

Key features

  1. 01Full-text Quran search
  2. 02Surah and verse navigation
  3. 03Lemma and root lookup
  4. 04Morphology queries
  5. 05stdio and Streamable HTTP transports

Use cases

  1. 01Retrieve exact Quran verses for a question
  2. 02Navigate to a surah or verse
  3. 03Look up Arabic lemmas and roots
  4. 04Inspect word morphology

MCP support

Exposes eight MCP tools for Quran search, navigation, metadata, lemma and root lookup, and morphology. Clients can connect over stdio or Streamable HTTP, including the hosted endpoint.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"adelpro-quran-search-engine": {
"command": "npx",
"args": [
"-y",
"quran-search-engine-mcp"
]
}
}
}
Run commandnpx -y quran-search-engine-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmquran-search-engine-mcp0.2.1

Tools

1

Saved tool list · updated 2w ago

ParameterTypeRequiredDescription
pageintegerNo
rootbooleanNo
lemmabooleanNo
limitintegerNo
querystringYes

Details

From the project README

Quran Search Engine MCP

npm version MCP Registry smithery badge license Powered by quran-search-engine quran-search-engine

An MCP (Model Context Protocol) server that gives AI clients fast, accurate, hallucination-free access to the Quran — search, navigation, and morphology — over stdio and Streamable HTTP.

Search, navigate, and explore the Quran through 8 MCP tools — verses, surahs, lemmas, roots, and morphology. Hosted at mcp.quran.us.kg. Instead of relying on an AI to "hallucinate" or predict Quranic verses, this tool routes every request to a dedicated search engine. The AI handles the natural language; the server returns the exact, literal Quranic text.

Public endpoint

The server is publicly hosted at https://mcp.quran.us.kg/ (Cloudflare-fronted, stable). No API key, no auth — the endpoint is open and CORS-enabled for any client.

ResourceURL
MCP server (Streamable HTTP)https://mcp.quran.us.kg/
Health checkhttps://mcp.quran.us.kg/health
Status pagehttps://quran.us.kg

Features

  • 🔌 MCP compatible — Claude Desktop, Claude Web, ChatGPT, Cursor, VS Code, and others.
  • 🌐 Two transports — stdio for local integrations, Streamable HTTP for remote/hosted.
  • 🔍 Eight tools — full-text search, surah metadata, verse navigation, lemma/root lookup, morphology.
  • 📖 Accurate results — every verse comes from a verified dataset; no LLM in the loop.
  • 🛡️ Hardened HTTP — host allow-list, per-IP rate limit, body cap, session reaper, /health.

Install

# Use the public endpoint
# → point your MCP client at https://mcp.quran.us.kg/

# Or run the server locally (stdio)
npx -y quran-search-engine-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, dataset loading, HTTP hardening.
  • Development — build, test, add a new tool, deploy.

Quick start (HTTP)

The shortest path: use any MCP client and point it at https://mcp.quran.us.kg/. For ad-hoc testing, the integrations page shows a one-off Node snippet that uses @modelcontextprotocol/sdk directly.

Quick start (Docker)

docker compose up --build
# → "Quran MCP HTTP server listening on http://0.0.0.0:4000/"

Requirements

  • Node.js 20+ (LTS recommended)
  • npm, pnpm, or yarn

License

MIT — see LICENSE.

Contact

Email: [email protected]

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.