ForkFree

MCP servers

yarr

by dinglebear-ai

Yarr is a server and command-line tool that lets AI assistants and people control a self-hosted media setup, including Sonarr, Radarr, Plex, Jellyfin and related apps, through one consistent interface. It is for checking status and running actions across these services without building separate integrations for each.

Worth a lookEstablished, with a few things to check (listed below).

View on GitHubProject website

Stars
17
Licence
AGPL-3.0
Runs on
Your computer
Setup
Moderate
Language
Rust
Age
164 days

What you can do with it

  • Check the status of all your Sonarr, Radarr, Plex and other media services from one command or AI chat
  • Let Claude Code, Codex or Gemini CLI query and control your media apps through MCP
  • Save and re-run multi-step media automation scripts as reusable snippets

Make money with it

Someone could offer paid homelab or media-server setup and upkeep for clients, using this to speed up routine checks and changes.

An idea, not financial advice. Check the licence before charging for anything built on it.

Ways a business could use it

  • Manage a client's or your own self-hosted media server estate from a single AI-driven interface, saving admin time
  • Offer homelab setup and maintenance services where routine checks are handled through scripted commands

Can you use it commercially?

Free to use. Anything you distribute that includes it must be open-sourced under the same licence. Running it as an online service also counts, so a hosted version must offer its source.

Not legal advice. Read the project's licence file before building a product on it.

Add it to Claude Code

claude mcp add yarr -- npx -y @dinglebear/yarr

From the official MCP Registry (ai.dinglebear/yarr). Only connect MCP servers you trust: they can act on your behalf.

Getting it running

Install with the shell installer script, npm or an Unraid plugin, then set environment variables with each service's URL and API key.

Follow the official instructions in the project README.

Things to check

  • Small project with few stars, so support may be limited
  • Licensed under AGPL-3.0, which has obligations if you offer it as a network service
  • The README says the pinned npm package version was not yet available, so use the native installer
  • Aimed at media apps that are often used for piracy, so check you only manage content you have the rights to
  • Needs an AI client and API keys for each connected service

Checked 03 Nov 2026. Summary drafted by AI from the project's README.

More in MCP servers

kanzo emanuele-em
Hidden gem

Kanzo is a small kanban board that runs in your browser and also works as an MCP server, so you and your AI coding agents share the same task list. All data sits in one local folder, which can be synced between machines through a private git repository.

913 stars +155 a day AGPL-3.0
earshot Leonxlnx
New and promising

Earshot is a toolkit that lets AI coding agents analyse and describe audio, check how well sound fits a description or a video, and create their own sound effects in code. It runs locally on a CPU as a command-line tool, a Python library or an MCP server.

3.6k stars +85 a day MIT
huddo-mcp puffo-ai
New and promising

This is an MCP server and command-line tool that lets an AI agent join Huddo, a group chat where people and AI agents share the same room. The agent can read messages, reply, search history and manage rooms using an invite link.

5 stars MIT