dervish666/radarr-mcp-server

Radarr MCP Server

A Model Context Protocol (MCP) server that provides integration with Radarr for managing movies. This server allows AI assistants to interact with your Radarr instance to list movies, check calendars, search for new movies, and add movies to your collection.

Features

• List Movies: Retrieve all movies currently tracked by Radarr
• Calendar: Get upcoming and recently released movies
• Movie Lookup: Search for new movies by name
• Add Movie: Add new movies to Radarr with custom settings
• Get Movie Files: Retrieve all movie files for a specific movie
• Search Movie: Trigger Radarr to actively search for a specific movie

Prerequisites

• Node.js (version 14 or higher)
• npm or yarn
• A running Radarr instance
• Radarr API key

Installation

1. Clone this repository:

   git clone <repository-url>
   cd radarr-mcp-server
   

2. Install dependencies:

   npm install
   

3. Set up environment variables:

   cp .env.example .env
   

4. Edit the .env file with your Radarr configuration:

   PORT=12010
   RADARR_URL=http://your-radarr-host:7878
   RADARR_API_KEY=your-radarr-api-key-here
   

Getting Your Radarr API Key

1. Open your Radarr web interface
2. Go to Settings > General
3. Scroll down to the Security section
4. Copy the API Key

Environment Variables

• PORT: The port the MCP server will listen on (default: 12010)
• RADARR_URL: The full URL to your Radarr instance
• RADARR_API_KEY: Your Radarr API key

Usage

Development

Run the server in development mode with hot reloading:

npm run dev

Production

Build and run the server:

npm run build
npm start

Health Check

The server provides a health check endpoint:

curl http://localhost:12010/health

MCP Endpoint

The main MCP endpoint is available at:

POST http://localhost:12010/mcp

Available Tools

1. listMovies: Get all movies tracked by Radarr
2. getCalendar: Get upcoming/recent movies (optional date range)
3. lookupMovie: Search for new movies by name
4. addMovie: Add a new movie to Radarr
5. getMovieFiles: Get all movie files for a specific movie
6. searchMovie: Trigger Radarr to search for a specific movie

Integration with AI Assistants

This server implements the Model Context Protocol (MCP) and can be integrated with compatible AI assistants. The server supports both standard MCP protocol and legacy tool discovery for backward compatibility.

Example MCP Request

{
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "name": "listMovies",
    "arguments": {}
  },
  "id": 1
}

Docker Support

A Dockerfile is included for containerized deployment:

docker build -t radarr-mcp-server .
docker run -p 12010:12010 --env-file .env radarr-mcp-server

Troubleshooting

Common Issues

1. Connection refused: Ensure Radarr is running and accessible at the configured URL
2. Unauthorized: Verify your API key is correct
3. Port already in use: Change the PORT in your .env file

Logs

The server logs all requests and errors to the console. Check the logs for detailed error information.

API Differences from Sonarr

This server is adapted from the Sonarr MCP server with the following key differences:

• Uses TMDB ID instead of TVDB ID for movie identification
• Movie-focused endpoints instead of series/episodes
• Movie files instead of episode files
• Physical/Digital release dates instead of air dates
• Different search commands specific to Radarr's movie search functionality

Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

License

ISC License