Torbox Mcp — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Torbox Mcp (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
<p align="center"> <img src="https://img.shields.io/badge/Python-3.10%2B-blue" alt="Python"> <img src="https://img.shields.io/badge/Framework-FastMCP-green" alt="Framework"> <img src="https://img.shields.io/badge/License-MIT-lightgrey" alt="License"> </p>
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.
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt.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 python src/server.pyThe SSE endpoint is http://localhost:8000/sse. The server binds to 0.0.0.0:8000 by default so that it remains reachable through Docker port publishing. MCP_HOST and MCP_PORT may be used to override the bind address for non-Docker deployments.
To run the complete stack in Docker:
docker compose up --build -dIn Docker, Prowlarr is reached by its Compose service name at http://prowlarr:9696; do not use localhost for this connection. The localhost value in the local .env example is only for running the MCP server directly on the host.
Prowlarr indexers protected by Cloudflare can take longer than a typical HTTP request. Searches wait up to 120 seconds by default; set PROWLARR_SEARCH_TIMEOUT to change that limit.
The Docker defaults cap in-flight work to prevent slow external services from piling up inside the MCP process:
MAX_CONCURRENT_PROWLARR_SEARCHES=5
MAX_CONCURRENT_TORBOX_OPS=3
METADATA_MAX_RETRIES=30
METADATA_RETRY_DELAY=5Torrent files downloaded from Prowlarr are accepted without a size cap. To reduce peak memory use, the server spools larger .torrent payloads to the container temp directory before uploading them to TorBox.
The server exposes tools to your AI agent natively over MCP:
search_indexersadd_to_cloudinspect_file_treeget_secure_linkMIT License
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.