Torrent Search MCP Server & API

This repository provides a Python API and an MCP (Model Context Protocol) server to find torrents programmatically on ThePirateBay, Nyaa, 1337x, YTS, FitGirl, EZTV, SubsPlease and BitTorrented. It allows for easy integration into other applications or services.

Quickstart

How to use it with MCP Clients

Run it with Docker to bypass common DNS issues

Search directly from the command line

# One-time setup: install playwright/chromium for crawl4ai
uvx --from torrent-search-mcp crawl4ai-setup

# CLI search
uvx torrent-search-mcp --mode cli "breaking bad"

# MCP server over stdio (default)
uvx torrent-search-mcp --mode stdio

# MCP server over streamable HTTP (port 8000, endpoint /mcp)
uvx torrent-search-mcp --mode http

# MCP server over SSE (port 8000, endpoint /sse, legacy)
uvx torrent-search-mcp --mode sse

# Standalone FastAPI server (port 8000)
uvx torrent-search-mcp --mode fastapi

Table of Contents

• Features
• Supported Sources
• Setup
  • Prerequisites
  • Configuration
  • Installation
    • Install from PyPI (Recommended)
    • For Local Development
    • For Docker
• Usage
  • As CLI
  • As Python Wrapper
  • As MCP Server
  • As FastAPI Server
  • Via MCP Clients
    • Example with Devin
• Changelog
• Contributing
• License

Features

• API wrapper for ThePirateBay, Nyaa, 1337x, YTS, FitGirl, EZTV, SubsPlease and BitTorrented.
• MCP server interface for standardized communication (stdio, sse, streamable-http).
• FastAPI server interface for alternative HTTP access (e.g., for direct API calls or testing).
• CLI mode for quick one-off searches directly from the terminal.
• In-memory + aiocache result caching to reduce redundant scraping.
• Configurable source filtering and torrent file download folder via environment variables.
• Tools:
  • Search for torrents across all available sources.
  • Get magnet link or torrent file for a specific torrent by id.

Supported Sources

Sources can be excluded individually via the EXCLUDE_SOURCES env var.

Setup

Prerequisites

• Python 3.10+ (required for PyPI install). CI and Docker images use Python 3.14.
• uv (for local development).
• Docker and Docker Compose (for Docker setup).

Configuration (Optional)

The application reads configuration from environment variables. The recommended way to set them is by creating a .env file in your project's root directory. The application will load it automatically. See .env.example for all available options.

Installation

Choose one of the following installation methods.

Install from PyPI (Recommended)

This method is best for using the package as a library or running the server without modifying the code.

1. Install the package from PyPI:

pip install torrent-search-mcp
crawl4ai-setup # For crawl4ai/playwright
playwright install --with-deps chromium # If previous command fails

2. Create a .env file in the directory where you'll run the application (optional).

3. Run the MCP server (default: stdio):

python -m torrent_search

For Local Development

This method is for contributors who want to modify the source code. Using uv:

1. Clone the repository:

git clone https://github.com/philogicae/torrent-search-mcp.git
cd torrent-search-mcp

2. Install dependencies using uv:

uv sync --frozen
uvx playwright install --with-deps chromium

3. Create your configuration file by copying the example:

cp .env.example .env

4. Run the MCP server (default: stdio):

uv run -m torrent_search

The repo also ships a dev.sh helper that locks/syncs deps, formats, lints, type-checks (ty) and runs the test suite with coverage:

./dev.sh

For Docker

This method uses Docker to run the server in a container.

compose.yaml is configured to bypass DNS issues (using quad9 DNS). The container runs the server in http (streamable-http) mode on port 8000 (endpoint /mcp) and persists downloaded torrent files to a named volume.

1. Clone the repository (if you haven't already):

git clone https://github.com/philogicae/torrent-search-mcp.git
cd torrent-search-mcp

2. Create your configuration file by copying the example:

cp .env.example .env

3. Build and run the container using Docker Compose (default port: 8000):

docker compose up --build -d

4. Access container logs:

docker logs torrent-search-mcp -f

Usage

The package exposes a single entry point, torrent-search-mcp (installed by pip/uvx), equivalent to python -m torrent_search. It supports the following --mode values:

Common flags (for http, streamable-http, sse and fastapi modes): --host (default 0.0.0.0), --port (default 8000), --reload, --workers (FastAPI only).

As CLI

Run a one-off search directly from the terminal. Prints each result as id (seeders|leechers|downloads) - filename, then fetches the magnet/torrent for the top hit.

# Using the installed entry point
torrent-search-mcp --mode cli "breaking bad"

# Or via uvx without installing
uvx torrent-search-mcp --mode cli "breaking bad"

# Or from source
uv run -m torrent_search --mode cli "breaking bad"

As Python Wrapper

from torrent_search import torrent_search_api

results = await torrent_search_api.search_torrents("breaking bad")
for torrent in results:
    print(
        f"{torrent.filename} | {torrent.size} | {torrent.seeders} SE | {torrent.leechers} LE | {torrent.date} | {torrent.source}"
    )

search_torrents is async and accepts an optional max_items (default 10). Each Torrent exposes id, filename, size, seeders, leechers, date, source, and (when available) magnet_link / torrent_file. Pass a torrent's id to get_torrent() to retrieve its magnet link or .torrent file path.

As MCP Server

from torrent_search import torrent_search_mcp

torrent_search_mcp.run(transport="sse")

As FastAPI Server

This project also includes a FastAPI server as an alternative way to interact with the library via a standard HTTP API. This can be useful for direct API calls, integration with other web services, or for testing purposes.

Running the FastAPI Server:

# With Python
python -m torrent_search --mode fastapi
# With uv
uv run -m torrent_search --mode fastapi

• --host <host>: Default: 0.0.0.0.
• --port <port>: Default: 8000.
• --reload: Enables auto-reloading when code changes (useful for development).
• --workers <workers>: Default: 1.

The FastAPI server will then be accessible at http://<host>:<port>.

Available Endpoints: The FastAPI server exposes similar functionalities to the MCP server. Key endpoints include:

• GET /: Health check endpoint. Returns {"status": "ok"}.
• POST /torrent/search: Search for torrents. Query params: query (required) and max_items (optional, default 10).
• GET /torrent/{torrent_id}: Get the magnet link or .torrent file for a specific torrent by id. Returns the magnet URI as text, or streams the .torrent file.
• /docs: Interactive API documentation (Swagger UI).
• /redoc: Alternative API documentation (ReDoc).

Environment variables are configured the same way as for the MCP server (via an .env file in the project root).

Via MCP Clients

Usable with any MCP-compatible client. Available tools:

• search_torrents(user_intent, query): Search for torrents across all available sources.
  • user_intent: A short description reflecting the user's overall intention (e.g. "latest episode of Breaking Bad").
  • query: Optimized, lowercase, space-separated keywords (e.g. "breaking bad s01e05"). Generic/filler/technical terms should be stripped per the tool's docstring.
  • By default magnet links are stripped from the response to save tokens; set INCLUDE_LINKS=true to include them.
• get_torrent(torrent_id): Get the magnet link or torrent file path for a specific torrent by id (the id returned by search_torrents).

Available resources:

• data://torrent_sources: Get the list of available torrent sources.

Example with Devin

Configuration:

{
  "mcpServers": {
    ...
    # with stdio (only requires uv)
    "torrent-search-mcp": {
      "command": "uvx",
      "args": [ "torrent-search-mcp" ]
    },
    # with streamable-http transport (Docker default; requires running server)
    "torrent-search-mcp": {
      "serverUrl": "http://127.0.0.1:8000/mcp"
    },
    # with sse transport (legacy; requires running server)
    "torrent-search-mcp": {
      "serverUrl": "http://127.0.0.1:8000/sse"
    },
    ...
  }
}

Changelog

See CHANGELOG.md for a history of changes to this project.

Contributing

Contributions are welcome! Please open an issue or submit a pull request.

License

This project is licensed under the MIT License - see the LICENSE file for details.