Mondweep Youtube Music MCP Server

🚀 YouTube Music MCP Server

This project implements a Model Context Protocol (MCP) server that enables AI models to control YouTube Music playback via Google Chrome. It bridges the gap between AI assistants and music playback, allowing AIs to search for and play songs based on song names and artist names.

🚀 Quick Start

This YouTube Music MCP server serves as a bridge for AI models to interact with YouTube Music through Google Chrome. With it, AI assistants can search for and play music on YouTube Music.

✨ Features

• Search for songs on YouTube Music.
• Play songs directly in Google Chrome.
• Support searches by song name and artist name.
• Error handling and logging.
• Cross - platform support (mainly for Chrome automation on macOS).

📦 Installation

When using it with Claude Desktop, add the server configuration:

On macOS: ~/Library/Application Support/Claude/claude_desktop_config.json On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "youtube-music-server": {
      "command": "/path/to/youtube-music-server/build/index.js"
    }
  }
}

Debugging

Since MCP servers communicate via standard input and output, debugging can be challenging. We recommend using the MCP Inspector, which is provided as a package script:

npm run inspector

The inspector will provide a URL to access the debugging tools in the browser.

💻 Usage Examples

Basic Usage

Install dependencies:

npm install

Build the server:

npm run build

Development with automatic rebuild:

npm run watch

📚 Documentation

What is MCP?

The Model Context Protocol (MCP) is a standard method for AI models to interact with external tools and services. It provides a structured communication protocol that enables AI assistants to:

• Discover available tools.
• Understand the functions of tools.
• Execute actions through these tools.
• Handle consistent responses and errors.

Learn more about MCP:

• MCP Documentation
• MCP SDK

Architecture

High - level Overview

This is a TypeScript - based MCP server that demonstrates core MCP concepts by providing the following features:

• List and access text notes via note:// URIs.
• Each note has a title, content, and metadata.
• A tool to create new notes.
• A prompt to generate a summary of all stored notes.

Features

Resources

• List and access notes via note:// URIs.
• Each note has a title, content, and metadata.
• Simple text MIME type for easy content access.

Tools

• create_note - Create a new text note.
  • Use title and content as required parameters.
  • Store the note in the server state.

Prompts

• summarize_notes - Generate a summary of all stored notes.
  • Include all note content as embedded resources.
  • Return a structured prompt for LLM summarization.