rqbit
Interact with the rqbit torrent client API. Requires a running rqbit instance.
Python API Wrapper & MCP Server for rqbit
This repository provides a Python API wrapper and an MCP (Model Context Protocol) server for the rqbit torrent client. It allows for easy integration into other applications or services.
Table of Contents
Features
- API wrapper for the
rqbittorrent client. - MCP server interface for standardized communication (stdio, sse, streamable-http)
- Tools:
list_torrents: List all torrents and their details.download_torrent: Download a torrent from a magnet link or a file.get_torrent_details: Get detailed information about a specific torrent.get_torrent_stats: Get stats/status of a specific torrent.pause_torrent: Pause a torrent.start_torrent: Start a torrent.forget_torrent: Forget a torrent, keeping the files.delete_torrent: Delete a torrent and its files.
Setup
Prerequisites
- An running instance of rqbit. (Included in docker compose)
- Python 3.10+ (required for PyPI install).
uv(for local development)
Configuration
This application requires the URL of your rqbit instance.
Set Environment Variable: Copy .env.example to .env in your project's root directory and edit it with your settings. The application will automatically load variables from .env:
- MCP Server:
RQBIT_URL: The URL of the rqbit instance (Default:http://localhost:3030).RQBIT_HTTP_BASIC_AUTH_USERPASS: If setup in rqbit instance.
- Rqbit Instance:
RQBIT_HTTP_BASIC_AUTH_USERPASS: The username and password for basic authentication, in the formatusername:password.RQBIT_HTTP_API_LISTEN_ADDR: The listen address for the HTTP API (e.g.,0.0.0.0:3030).RQBIT_UPNP_SERVER_ENABLE: Enables or disables the UPnP server (e.g.,trueorfalse).RQBIT_UPNP_SERVER_FRIENDLY_NAME: The friendly name for the UPnP server (e.g.,rqbit-media).RQBIT_EXPERIMENTAL_UTP_LISTEN_ENABLE: Enables or disables the uTP listener (Default:false).- Check rqbit for other variables and more information.
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 rqbit-mcp
- Create a
.envfile in the directory where you'll run the application and add yourrqbitURL:
RQBIT_URL=http://localhost:3030
- Run the MCP server (default: stdio):
python -m rqbit_client
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/rqbit-mcp.git
cd rqbit-mcp
- Install dependencies using
uv:
uv sync --locked
- Create your configuration file by copying the example and add your settings:
cp .env.example .env
- Run the MCP server (default: stdio):
uv run -m rqbit_client
For Docker
This method uses Docker to run the server in a container. compose.yaml includes rqbit torrent client.
- Clone the repository (if you haven't already):
git clone https://github.com/philogicae/rqbit-mcp.git
cd rqbit-mcp
- Create your configuration file by copying the example and add your settings:
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 rqbit-mcp -f
Usage
As Python API Wrapper
import asyncio
from rqbit_client.wrapper import RqbitClient
async def main():
# Read the RQBIT_URL from the .env file or fallback to default (http://localhost:3030)
async with RqbitClient() as client:
# Download a torrent
magnet_link = "magnet:?xt=urn:btih:..."
torrent = await client.download_torrent(magnet_link)
print(torrent)
# Check status
status = await client.get_torrent_stats(torrent["id"])
print(status)
# List torrents
torrents = await client.list_torrents()
print(torrents)
if __name__ == "__main__":
asyncio.run(main())
As MCP Server
from rqbit_client import RqbitMCP
RqbitMCP.run(transport="sse") # 'stdio', 'sse', or 'streamable-http'
Via MCP Clients
Usable with any MCP-compatible client. Available tools:
list_torrents: List all torrents.download_torrent: Download a torrent via magnet link or file path.get_torrent_details: Get details of a specific torrent.get_torrent_stats: Get stats/status of a specific torrent.pause_torrent: Pause a torrent.start_torrent: Start a torrent.forget_torrent: Forget a torrent, keeping the files.delete_torrent: Delete a torrent and its files.
Example with Windsurf
Configuration:
{
"mcpServers": {
...
# with stdio (only requires uv)
"rqbit-mcp": {
"command": "uvx",
"args": [ "rqbit-mcp" ],
"env": {
"RQBIT_URL": "http://localhost:3030", # (Optional) Default rqbit instance URL
"RQBIT_HTTP_BASIC_AUTH_USERPASS": "username:password" # (Optional) Only if setup in rqbit instance
}
},
# with docker (only requires docker)
"rqbit-mcp": {
"command": "docker",
"args": [ "run", "-i", "-p", "8000:8000", "-e", "RQBIT_URL=http://localhost:3030", "-e", "RQBIT_HTTP_BASIC_AUTH_USERPASS=username:password", "philogicae/rqbit-mcp:latest", "rqbit-mcp" ]
},
# with sse transport (requires installation)
"rqbit-mcp": {
"serverUrl": "http://127.0.0.1:8000/sse"
},
# with streamable-http transport (requires installation)
"rqbit-mcp": {
"serverUrl": "http://127.0.0.1:8000/mcp"
},
...
}
}
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.
Related Servers
mcp-whatsapp
Local MCP server for a personal WhatsApp account. Single Go binary wrapping whatsmeow. Adds LID resolution, sent-message storage, disappearing-message timers, targeted history sync. Personal-use; Meta ToS applies.
Ayni Protocol
Visual coordination protocol for AI agents — 22 MCP tools for glyph-based communication with 50-70% token savings, shared memory, governance, and on-chain attestation.
Voyp
Integrate AI assistants with VOYP's calling capabilities to make calls, search business info, and manage call status.
Phone-a-Friend MCP Server
An AI-to-AI consultation system for complex problem-solving and reasoning, using OpenRouter for model access.
Multichat MCP Server
A server for handling parallel unichat requests, configurable via a settings file.
Apple Notifier
Send native macOS notifications and interact with system dialogs.
Telnyx
Official Telnyx remote MCP server for AI agents.
Prompt for User Input MCP Server
Enables AI models to prompt users for input directly within their code editor for interactive conversations.
Africa's Talking Airtime MCP
Interact with Africa's Talking airtime service and store transaction data in a local SQLite database.
Concordia Protocol
Open negotiation standard for AI agents — structured proposals, binding commitments, and verifiable session receipts