mcpField
Y
YouTube Music MCP 🎵

YouTube Music MCP 🎵

Local
github.com/instructaMedia & Design12Updated 81w ago
Repository

About YouTube Music MCP 🎵

YouTube Music MCP is a server for AI assistants that searches YouTube Music and opens selected tracks for playback in the default browser. It requires a Google YouTube API key.

Key features

  1. 01Search YouTube Music tracks
  2. 02Open tracks in the default browser

Use cases

  1. 01Find a track by name
  2. 02Open a selected track for playback

MCP support

Provides `searchTrack` and `playTrack` tools to MCP clients. The playback tool searches for a track and opens it in the default browser.

#youtube-music#mcp-server#music-assistant

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "youtube-music": {
      "command": "npx",
      "args": [
        "-y",
        "@instructa/mcp-youtube-music"
      ],
      "env": {
        "YOUTUBE_API_KEY": "<YOUTUBE_API_KEY>"
      }
    }
  }
}
Run commandnpx -y @instructa/mcp-youtube-music
Environment variables to set
YOUTUBE_API_KEYSecret

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@instructa/mcp-youtube-music

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

YouTube Music MCP 🎵

This is a simple MCP server that allows you to search for and play tracks on YouTube Music directly from your AI assistant like Cursor or Claude Desktop.

Built with:

Available Tools

  • searchTrack: Search for tracks on YouTube Music by name.
  • playTrack: Play tracks directly by searching and opening them in your default browser.

Installation

1. Get a key

To make this work you need a valid Google Youtube API Key

2. Add to cursor

Add the following MCP configuration to your Cursor .cursor/mcp.json settings:

{
  "mcpServers": {
    "youtube-music-mcp": {
      "command": "npx",
      "args": ["-y", "@instructa/mcp-youtube-music"],
      "env": {
        "YOUTUBE_API_KEY": "<INSERT_API_KEY_HERE>"
      }
    }
  }
}

Develop

This MCP is typically run directly using npx and doesn't require local installation or building unless you intend to modify the source code. If you want to develop it locally, you would typically clone the source repository (if available) and follow its specific contribution guidelines.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Links

Courses

See my other projects:

  • AI Prompts - Curated AI Prompts for Cursor AI, Cline, Windsurf and Github Copilot
  • codefetch - Turn code into Markdown for LLMs with one simple terminal command
  • aidex A CLI tool that provides detailed information about AI language models, helping developers choose the right model for their needs.
  • codetie - XCode CLI

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.