Allows for searching the YouTube Music catalog for songs, albums, artists, and playlists, as well as managing user playlists through actions such as creating, listing, adding tracks, and deleting.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@mcp-ytmusic Add 'Starboy' by The Weeknd to my 'Favorites' playlist"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
YouTube Music MCP server for Claude Code. Search the catalog and manage playlists via natural language.
Tool | Actions | Description |
| — | Search songs, videos, albums, artists, playlists |
|
| Manage playlists |
|
| Check configuration and auth |
Related MCP server: YouTube Music MCP Server
# Clone and install
git clone https://github.com/alexcook/mcp-ytmusic.git
cd mcp-ytmusic
python3 -m venv venv
source venv/bin/activate
pip install -e .
# Initialize config directory
ytmusic-mcp init
# Authenticate (paste browser headers from Chrome DevTools on music.youtube.com)
ytmusic-mcp auth
# Verify
ytmusic-mcp statusAdd to ~/.claude/mcp.json:
{
"mcpServers": {
"YouTube Music": {
"command": "/path/to/mcp-ytmusic/venv/bin/python",
"args": ["-m", "ytmusic_mcp"]
}
}
}Uses browser cookie authentication via ytmusicapi. One-time setup:
Open Chrome → https://music.youtube.com (make sure you're logged in)
Open DevTools (F12) → Network tab
Click any request to music.youtube.com
Right-click → Copy → Copy request headers
Run ytmusic-mcp auth and paste when prompted
Credentials are saved to ~/.config/ytmusic-mcp/browser.json and are valid for ~2 years.
This server cannot be deployed
AI playlist engine that turns music prompts into real YouTube playlists and filters bad versions.
YouTube transcripts, search, channel/playlist listings and upload tracking for AI agents.
YouTube transcripts, search, channel browsing, and playlists for AI agents via MCP.
Search YouTube, read video metadata, and fetch transcripts with language preferences
