gptdarr
A MCP Server for efficiently managing and automating TV shows and movies in Sonarr and Radarr setups. Simplify your media library management with AI-driven insights and commands.
Documentation
GPTDARR - Sonarr & Radarr MCP Server
Description
GPTDARR is an AI tool server using Model Context Protocol (MCP) that integrates with Sonarr and Radarr. It helps AI assistants search, add, and manage TV shows and movies in your media library.
Features
- Search for TV shows and movies across Sonarr and Radarr
- Add TV series to Sonarr
- Add movies to Radarr
- Comprehensive logging system for debugging and monitoring (sorry about the litter, this is very much a work in progress application)
Current Limitations
- Works best with movies; TV show support is more limited
- Does not support individual season and episode file checks
- Monitoring toggles are not implemented (unmonitored items are ignored)
- Prone to hallucinating tool-usage, make sure it runs the tool.
Todo
- [ ] Implement individual season and episode file checks
- [ ] Add support for toggling monitoring status
- [ ] Improve TV show support to match movie functionality
- [ ] Override quality profile through natural language
- [ ] Improve tool naming and descriptions so the LLM doesn't hallucinate tool calls (looking for expert advice here)
- [ ] Improve LLM system prompt to reduce hallucinations (looking for expert advice here too)
Getting Started
Prerequisites
- Node.js 18 or higher
- Sonarr and Radarr set up and running
- An MCP-compatible chat client (e.g., 5ire, Claude)
Installation & Setup
1. Run the interactive configuration wizard:
npx gptdarr setup2. The wizard will guide you through setting up:
3. After completing the setup, the wizard will generate an NPX command (recommended). Copy this command.
4. In your MCP-compatible chat client (e.g., 5ire):
5. Important: System Prompt
The server provides the following tools:
- lookup-content: Search for TV shows and movies
- Parameters:
- `title`: The title to search for
- `year` (optional): Release year to refine search
- Parameters:
- add-series: Add TV series to Sonarr
- Parameters:
- `items`: List of TV series to add, each with:
- `seriesName`: Name of the TV series
- `seriesYear` (optional): Year of the TV series
- `items`: List of TV series to add, each with:
- Parameters:
- add-movies: Add movies to Radarr
- Parameters:
- `items`: List of movies to add, each with:
- `title`: Title of the movie
- `year` (optional): Year of the movie
- `items`: List of movies to add, each with:
- Parameters:
Logging
The logs are mostly for development, and we suggest disabling them when running setup.
- Content lookups
- Series and movie additions
- API requests and responses
- Errors and exceptions
Logs are stored in your home directory in a `.gptdarr` folder.
Contributing
Contributions are welcome! Please read our Contributing Guide for more information.
License
This project is licensed under the MIT License.
Frequently asked questions
What is gptdarr?
gptdarr is A MCP Server for efficiently managing and automating TV shows and movies in Sonarr and Radarr setups. Simplify your media library management with AI-driven insights and commands.
How do I install gptdarr?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is gptdarr open source?
Yes — it is hosted on GitHub at https://github.com/csmit195/gptdarr and has 3 stars.
Related MCP tools
The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others. Built for the Model Context Protocol to enhance AI capabiliti
Fay是一个帮助数字人(2.5d、3d、移动、pc、网页)或大语言模型(openai兼容、deepseek)连通业务系统的mcp框架。 JavaScript-based implementation. Trusted by 12000+ developers.
CTTF: MCP integration between Cursor and Figma, allowing Cursor Agentic AI to communicate with Figma for reading designs and modifying them programmatically.
🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients. JavaScript-based implementation.
This is MCP server for Claude that gives it terminal control, file system search and diff file editing capabilities JavaScript-based implementation.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP