Skip to content

Knuckles-Team/qbittorrent-agent

Repository files navigation

qBittorrent Manager - A2A | AG-UI | MCP

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub

GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues

GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 0.1.7

Overview

qBittorrent Manager MCP Server + A2A Agent

AI agent for qBittorrent management, RSS automation, and search.

This repository is actively maintained - Contributions are welcome!

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

  • QBITTORRENT_URL: The URL of the target service.
  • QBITTORRENT_PASSWORD: The API token or access token.

Run in stdio mode (default):

export QBITTORRENT_URL="http://localhost:8080"
export QBITTORRENT_PASSWORD="your_token"
qbittorrent-mcp --transport "stdio"

Run in HTTP mode:

export QBITTORRENT_URL="http://localhost:8080"
export QBITTORRENT_PASSWORD="your_token"
qbittorrent-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export QBITTORRENT_URL="http://localhost:8080"
export QBITTORRENT_PASSWORD="your_token"
qbittorrent-agent --provider openai --model-id gpt-4o --api-key sk-...

Docker

Build

docker build -t qbittorrent-agent .

Run MCP Server

docker run -d \
  --name qbittorrent-agent \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e QBITTORRENT_URL="http://your-service:8080" \
  -e QBITTORRENT_PASSWORD="your_token" \
  knucklessg1/qbittorrent-agent:latest

Deploy with Docker Compose

services:
  qbittorrent-agent:
    image: knucklessg1/qbittorrent-agent:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - QBITTORRENT_URL=http://your-service:8080
      - QBITTORRENT_PASSWORD=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "qbittorrent": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "qbittorrent-agent",
        "qbittorrent-mcp"
      ],
      "env": {
        "QBITTORRENT_URL": "http://your-service:8080",
        "QBITTORRENT_PASSWORD": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install qbittorrent-agent
uv pip install qbittorrent-agent

Repository Owners

GitHub followers GitHub User's stars

About

QBittorrent Agent built on Pydantic Graph and QBittorrent MCP

Topics

Resources

License

Stars

Watchers

Forks

Packages

 
 
 

Contributors