YggTorrent MCP Server
Enables searching and downloading torrents from YggTorrent via MCP tools such as search_torrents, get_torrent_details, get_magnet_link, and download_torrent_file.
README
YggTorrent MCP Server & Wrapper
This repository provides a Python wrapper for the YggTorrent website and an MCP (Model Context Protocol) server to interact with it programmatically. This allows for easy integration of YggTorrent functionalities into other applications or services.
<a href="https://glama.ai/mcp/servers/@philogicae/ygg-torrent-mcp"> <img width="380" height="200" src="https://glama.ai/mcp/servers/@philogicae/ygg-torrent-mcp/badge?cache-control=no-cache" alt="YggTorrent Server MCP server" /> </a>
Quickstart
How to use it with MCP Clients Run it with Docker to bypass common DNS issues
Table of Contents
Features
- API wrapper for YggAPI, an unofficial API for YggTorrent
- Your Ygg passkey is injected locally into the torrent file/magnet link, ensuring it's not exposed externally
- 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)
- Tools:
- Search for torrents on YggTorrent
- Get details for a specific torrent
- Retrieve magnet links
- Retrieve torrent files
- Retrieve torrent categories
Setup
Prerequisites
- An active YggTorrent account and passkey.
- Python 3.10+ (required for PyPI install).
uv(for local development)- Docker and Docker Compose (for Docker setup)
Configuration
This application requires your YggTorrent passkey to interact with the API.
- Find your Passkey: On the YggTorrent website, navigate to
Mon compte->PASSKEYfield. - Set Environment Variable: The application reads the passkey from the
YGG_PASSKEYenvironment variable. The recommended way to set this is by creating a.envfile in your project's root directory. The application will load it automatically.
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.
- Install the package from PyPI:
pip install ygg-torrent-mcp
- Create a
.envfile in the directory where you'll run the application and add your passkey:
YGG_PASSKEY=your_passkey_here
- Run the MCP server (default: stdio):
python -m ygg_torrent
For Local Development
This method is for contributors who want to modify the source code.
Using uv:
- Clone the repository:
git clone https://github.com/philogicae/ygg-torrent-mcp.git
cd ygg-torrent-mcp
- Install dependencies using
uv:
uv sync --locked
- Create your configuration file by copying the example and add your passkey:
cp .env.example .env
- Run the MCP server (default: stdio):
uv run -m ygg_torrent
For Docker
This method uses Docker to run the server in a container.
compose.yaml is configured to bypass DNS issues (using quad9 DNS).
- Clone the repository (if you haven't already):
git clone https://github.com/philogicae/ygg-torrent-mcp.git
cd ygg-torrent-mcp
- Create your configuration file by copying the example and add your passkey:
cp .env.example .env
- Build and run the container using Docker Compose (default port: 8000):
docker compose up --build -d
- Access container logs:
docker logs ygg-torrent-mcp -f
Usage
As Python Wrapper
from ygg_torrent import ygg_api
results = ygg_api.search_torrents('...')
for torrent in results:
print(f"{torrent.filename} | {torrent.size} | {torrent.seeders} SE | {torrent.leechers} LE | {torrent.downloads} DL | {torrent.date}")
As MCP Server
from ygg_torrent import ygg_mcp
ygg_mcp.run(transport="sse")
As FastAPI Server
This project also includes a FastAPI server as an alternative way to interact with the YggTorrent functionalities 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 ygg_torrent --mode fastapi
# With uv
uv run -m ygg_torrent --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:
/: A simple health check endpoint. Returns{"status": "ok"}./docs: Interactive API documentation (Swagger UI)./redoc: Alternative API documentation (ReDoc).
Environment variables (like YGG_PASSKEY) 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: Search for torrents.get_torrent_details: Get details of a specific torrent.get_magnet_link: Get the magnet link for a torrent.download_torrent_file: Download the .torrent file for a torrent.
Example with Windsurf
Configuration:
{
"mcpServers": {
...
# with stdio (only requires uv installed)
"ygg-torrent-mcp": {
"command": "uvx",
"args": ["ygg-torrent-mcp"],
"env": { "YGG_PASSKEY": "your_passkey_here" }
}
# with sse transport (requires installation)
"ygg-torrent-mcp": {
"serverUrl": "http://127.0.0.1:8000/sse"
}
# with streamable-http transport (requires installation)
"ygg-torrent-mcp": {
"serverUrl": "http://127.0.0.1:8000/mcp" # not yet supported by every client
}
...
}
}
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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。