radarr-mcp

Part of the arr-mcps collection. MCP server exposing Radarr's v3 REST API (OpenAPI 3.0.4) as tools, so an LLM can read and manage a Radarr instance: movies, movie files, the download queue, history, indexers, import lists, custom formats, tags, commands, system status, and more. Full surface — reads and writes, with destructive tools flagged.

Built with FastMCP.

Getting an API key

Generate one in Radarr Settings > General > Security. Auth is the X-Api-Key header.

Related MCP server: Radarr and Sonarr MCP Server

Install

Download a wheel from the latest release and install it as a uv tool (no repo checkout needed):

uv tool install radarr_mcp-*.whl

This puts a radarr-mcp command on your PATH. Register it with Claude Code:

claude mcp add radarr \
  --env RADARR_URL=http://your-radarr-host:7878 \
  --env RADARR_API_KEY=<key> \
  -- radarr-mcp

From source

uv sync
cp .env.example .env   # fill in RADARR_URL and RADARR_API_KEY

claude mcp add radarr \
  --env RADARR_URL=http://your-radarr-host:7878 \
  --env RADARR_API_KEY=<key> \
  -- uv run --directory /path/to/radarr-mcp radarr-mcp

Config

* Every API endpoint requires auth; practically you must set it, but the server still starts without one so errors surface from the API rather than at startup.

Tools

15 resource-scoped tools, each covering multiple Radarr v3 endpoints (226 total) via an operation parameter. Call a tool with operation set to one of its listed operations and an arguments dict matching that operation's parameters — the tool's own description (visible to your MCP client) lists every operation, its signature, and a one-line doc. This keeps the full REST surface available while costing a fraction of the context budget of registering all 226 endpoints as separate tools.

Example: radarr_queue(operation="radarr_delete_queue", arguments={"id": 42}). Endpoint-level naming (radarr_<verb>_<resource>) is preserved as the operation value, so the full endpoint list is still discoverable from each group tool's description at runtime.

Development

make help  # list all commands

The release workflow (.github/workflows/release.yml) builds and publishes to Releases whenever a v* tag is pushed - so the usual flow is make bump-patch, commit, then tag and push.

The integration suite is read-only by default (GET endpoints only). Set RADARR_WRITE_TESTS=1 to also exercise POST/PUT/DELETE against a scratch tag (created, updated, then deleted). Never run write tests against a production library.