Radarr and Sonarr MCP Server

A Python-based Model Context Protocol (MCP) server that provides AI assistants like Claude with access to your Radarr (movies) and Sonarr (TV series) data.

Overview

This MCP server allows AI assistants to query your movie and TV show collection via Radarr and Sonarr APIs. Built with FastMCP, it implements the standardized protocol for AI context that Claude Desktop and other MCP-compatible clients can use.

Related MCP server: wizzy-mcp-tmdb

Features

• Native MCP Implementation: Built with FastMCP for seamless AI integration

• Radarr Integration: Full movie collection management — search, add, delete, monitor, grab releases

• Sonarr Integration: Full TV show management — episodes, seasons, monitoring, releases

• Episode-Level Control: Toggle monitoring for specific episodes or entire seasons with safety checks

• Targeted Search: Trigger searches for specific episodes in a season (e.g., S07E23, S07E24)

• Release Grabbing: Trigger live searches against indexers and grab specific releases

• Watch Status: Integration with Jellyfin/Plex for watched status tracking

• Rich Filtering: Filter by year, watched status, actors, download status, and more

• Claude Desktop Compatible: Works seamlessly with Claude's MCP client

• Easy Setup: Interactive configuration wizard

• Well-tested: Comprehensive test suite for reliability

Installation

From Source

1. Clone this repository:

   git clone https://github.com/yourusername/radarr-sonarr-mcp.git
   cd radarr-sonarr-mcp-python

2. Install the package:

   pip install -e .

Using pip (coming soon)

pip install radarr-sonarr-mcp

Quick Start

1. Configure the server:

   radarr-sonarr-mcp configure

   Follow the prompts to enter your Radarr/Sonarr API keys and other settings.

2. Start the server:

   radarr-sonarr-mcp start

3. Connect Claude Desktop:

   • In Claude Desktop, go to Settings > MCP Servers

   • Add a new server with URL: http://localhost:3000 (or your configured port)

Configuration

The configuration wizard will guide you through setting up:

• NAS/Server IP address

• Radarr API key and port

• Sonarr API key and port

• MCP server port

You can also manually edit the config.json file:

{
  "nasConfig": {
    "ip": "10.0.0.23",
    "port": "7878"
  },
  "radarrConfig": {
    "apiKey": "YOUR_RADARR_API_KEY",
    "basePath": "/api/v3",
    "port": "7878"
  },
  "sonarrConfig": {
    "apiKey": "YOUR_SONARR_API_KEY",
    "basePath": "/api/v3",
    "port": "8989"
  },
  "server": {
    "port": 3000
  }
}

Available MCP Tools

General

Radarr — Movies

Sonarr — TV Series

Sonarr — Search & Releases

Sonarr — Monitoring

Sonarr — Queue & History

Sonarr — System

MCP Resources

Filtering Options

Most tools support various filtering options:

• year — Filter by release year

• watched — Filter by watched status (true/false)

• downloaded — Filter by download status (true/false)

• actors — Filter by actor/cast name

Example Queries for Claude

Once your MCP server is connected to Claude Desktop, you can ask questions like:

• "What sci-fi movies from 2023 do I have?"

• "Show me TV shows starring Pedro Pascal"

• "Do I have any unwatched episodes of The Mandalorian?"

• "Find movies with Tom Hanks that I haven't watched yet"

• "How many episodes of Stranger Things do I have downloaded?"

• "Is Big Bang Theory in Sonarr?"

• "Trigger a search for Big Bang Theory S07E23 and S07E24"

• "Monitor all episodes of Big Bang Theory season 1"

• "What releases are available for Big Bang Theory season 7?"

• "Grab the first release from the indexers for Interstellar"

• "Unmonitor season 1 of The Big Bang Theory"

Finding API Keys

Radarr API Key

1. Open Radarr in your browser

2. Go to Settings > General

3. Find the "API Key" section

4. Copy the API Key

Sonarr API Key

1. Open Sonarr in your browser

2. Go to Settings > General

3. Find the "API Key" section

4. Copy the API Key

Command-Line Interface

The package provides a command-line interface:

• radarr-sonarr-mcp configure — Run configuration wizard

• radarr-sonarr-mcp start — Start the MCP server

• radarr-sonarr-mcp status — Show the current configuration

Development

Running Tests

To run the test suite:

# Install development dependencies
pip install -e ".[dev]"

# Run tests
pytest

# Run tests with coverage
pytest --cov=radarr_sonarr_mcp

Local Development

For quick development and testing:

# Run directly without installation
python run.py

Requirements

• Python 3.7+

• FastMCP

• Requests

• Pydantic

Notes

• The watched/watchlist status functionality assumes these are tracked using Jellyfin/Plex. Configure these in your config.json for watched status to work.

• For security reasons, it's recommended to run this server only on your local network.

• Episode and season monitoring tools include safety checks — they only toggle episodes that aren't already in the desired state, preventing accidental double-toggles.