TorBox MCP Server

A robust Model Context Protocol (MCP) server that connects your AI agents to Prowlarr and TorBox, allowing for fully autonomous torrent searching, downloading, and media extraction.

Features

• Search for torrents across indexers configured in Prowlarr.

• Send torrents and magnet links directly to TorBox for secure cloud downloading.

• Automatically handles indexer redirects and localhost proxies (e.g., FlareSolverr).

• Inspects downloaded TorBox file trees to extract specific media files.

• Generates secure streaming/download links for downloaded files.

• Built-in guardrails to reject executable files from media requests for security.

Related MCP server: Brainstorm

Requirements

• Python 3.10+

• TorBox Account (with API Key)

• Prowlarr Instance (Local or Remote)

• Docker (optional, for running Prowlarr/FlareSolverr via the included compose file)

Setup

1. Clone the repository.

2. Create a virtual environment and install dependencies:

   python -m venv venv
   source venv/bin/activate
   pip install -r requirements.txt

3. Copy .env.example to .env and fill in your details:

   PROWLARR_URL=http://localhost:9696
   PROWLARR_API_KEY=your_prowlarr_api_key_here
   TORBOX_API_KEY=your_torbox_api_key_here

4. Start the MCP server:

   python src/server.py

Usage

The server exposes tools to your AI agent natively over MCP:

• search_indexers

• add_to_cloud

• inspect_file_tree

• get_secure_link

License

MIT License