Apple Music Mcp
Description
# mcp-apple-music 🎵 [](https://www.python.org/downloads/) [](LICENSE)…
About
# mcp-apple-music 🎵 [](https://www.python.org/downloads/) [](LICENSE) [](https://modelcontextprotocol.io) An **MCP (Model…
Details
- Author
- Cifero74
- Downloads
- 207
- Categories
- Media
Jump to
- Search Apple Music catalog (songs, albums, artists, playlists)
- Search your personal library
- List library songs, albums, artists, and playlists
- Get tracks in a specific playlist
- Create new playlists
- Add tracks to playlists (library or catalog)
- View recently played albums, playlists, and stations
- Receive personalised Apple Music recommendations
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Apple Music McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Install Python 3.10+ and uv (recommended) or pip, clone the repository, run the one-time setup wizard (uv run mcp-apple-music-setup) to authorize via Apple’s MusicKit JS OAuth, then add the server to your Claude Desktop config with the uv run command pointing to the project directory. After restarting Claude, all 11 tools appear in the toolbar.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"apple music mcp": {
"apple-music": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/mcp-apple-music",
"mcp-apple-music"
]
}
}
}
}
McpServers
{
"apple-music": {
"command": "uv",
"args": [
"run",
"--directory",
"/absolute/path/to/mcp-apple-music",
"mcp-apple-music"
]
}
}
mcp-apple-music 🎵
An MCP (Model Context Protocol) server that gives Claude full access to your Apple Music account — search the catalog, browse your personal library, manage playlists, and explore your listening history and recommendations.
> Ask Claude things like:
> - "Based on what I've been listening to lately, recommend 15 songs I don't have yet and add them to a new playlist"
> - "Show me all my playlists and tell me which artists appear most"
> - "Search for albums by Nick Cave and add my three favourites to a playlist called Dark Picks"
---
Features
| Tool | Description |
|---|---|
| search_catalog | Search Apple Music catalog (songs, albums, artists, playlists) |
| search_library | Search within your personal library |
| get_library_songs | List songs saved in your library (paginated) |
| get_library_albums | List albums in your library (paginated) |
| get_library_artists | List artists in your library |
| get_library_playlists | List all your playlists with IDs |
| get_playlist_tracks | Get tracks inside a specific playlist |
| create_playlist | Create a new playlist |
| add_tracks_to_playlist | Add songs to a playlist (library or catalog tracks) |
| get_recently_played | See recently played albums/playlists/stations |
| get_recommendations | Get personalised Apple Music picks |
---
Requirements
- Python 3.10+
- uv (recommended) or pip
- An Apple Developer account (free tier is fine) with a MusicKit key
- An active Apple Music subscription
---
Setup
1. Create a MusicKit Key
1. Go to developer.apple.com → Certificates, Identifiers & Profiles
2. Under Keys, click + to create a new key
3. Give it any name, enable MusicKit, and click Continue → Register
4. Download the .p8 file — you can only download it once, keep it safe!
5. Note your Key ID (e.g. ABC123DEF4) and your Team ID (found under Membership Details)
> ⚠️ The Key ID is the alphanumeric code shown next to the key name — not the filename of the .p8 file.
2. Clone and install
```bash
git clone https://github.com/marioinghilleri/mcp-apple-music
cd mcp-apple-music
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
