Skip to main content
Glama
Spotify MCP Server

Spotify MCP Server

by boristopalov

spotify-mcp MCP server

MCP project to connect Claude with Spotify. Built on top of spotipy-dev's API.

Features

  • Start, pause, and skip playback

  • Search for tracks/albums/artists/playlists

  • Get info about a track/album/artist/playlist

  • Manage the Spotify queue

Related MCP server: Spotify MCP Server

Demo

Make sure to turn on audio

Configuration

Getting Spotify API Keys

Create an account on developer.spotify.com. Navigate to the dashboard. Create an app with redirect_uri as http://localhost:8888. (You can choose any port you want but you must use http and localhost). I set "APIs used" to "Web Playback SDK".

Run this project locally

This project is not yet set up for ephemeral environments (e.g. uvx usage). Run this project locally by cloning this repo

git clone https://github.com/varunneal/spotify-mcp.git

Add this tool as a mcp server.

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

"spotify": {
    "command": "uv",
    "args": [
      "--directory",
      "/path/to/spotify_mcp",
      "run",
      "spotify-mcp"
    ],
    "env": {
      "SPOTIFY_CLIENT_ID": YOUR_CLIENT_ID,
      "SPOTIFY_CLIENT_SECRET": YOUR_CLIENT_SECRET,
      "SPOTIFY_REDIRECT_URI": "http://localhost:8888"
    }
  }

Troubleshooting

Please open an issue if you can't get this MCP working. Here are some tips:

  1. Make sure uv is updated. I recommend version >=0.54.

  2. Make sure claude has execution permisisons for the project: chmod -R 755.

  3. Ensure you have Spotify premium (needed for running developer API).

TODO

Unfortunately, a bunch of cool features have now been deprecated from the Spotify API. Most new features will be relatively minor or for the health of the project:

  • tests.

  • adding API support for managing playlists.

  • adding API support for paginated search results/playlists/albums.

Deployment

(todo)

Building and Publishing

To prepare the package for distribution:

  1. Sync dependencies and update lockfile:

uv sync
  1. Build package distributions:

uv build

This will create source and wheel distributions in the dist/ directory.

  1. Publish to PyPI:

uv publish

Note: You'll need to set PyPI credentials via environment variables or command flags:

  • Token: --token or UV_PUBLISH_TOKEN

  • Or username/password: --username/UV_PUBLISH_USERNAME and --password/UV_PUBLISH_PASSWORD

Debugging

Since MCP servers run over stdio, debugging can be challenging. For the best debugging experience, we strongly recommend using the MCP Inspector.

You can launch the MCP Inspector via npm with this command:

npx @modelcontextprotocol/inspector uv --directory /Users/varun/Documents/Python/spotify_mcp run spotify-mcp

Upon launching, the Inspector will display a URL that you can access in your browser to begin debugging.

Available Tools

4 tools
SpotifyGetInfoC

Get detailed information about a Spotify item (track, album, artist, or playlist).

Inputs: item_id (required), qtype.

SpotifyPlaybackB

Manages the current playback with the following actions: - get: Get information about user's current track. - start: Starts of resumes playback. - pause: Pauses current playback. - skip: Skips current track.

Inputs: action (required), track_id, num_skips.

SpotifyQueueB

Manage the playback queue - get the queue or add tracks.

Inputs: action (required), track_id.

SpotifySearchB

Search for tracks, albums, artists, or playlists on Spotify.

Inputs: query (required), qtype, limit.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.5/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: GetInfo retrieves metadata, Playback controls active listening, Queue manages upcoming tracks, and Search finds new content. The separation between Playback (current track control) and Queue (future track management) is particularly well-defined.

    Naming Consistency5/5

    All tools follow a perfect 'Spotify[Action]' naming pattern with consistent PascalCase throughout. The pattern is immediately recognizable and predictable across all four tools.

    Tool Count5/5

    Four tools is ideal for this music streaming domain - it covers the essential workflows (discovery, playback control, queue management, and information lookup) without being overwhelming or sparse. Each tool earns its place in the set.

    Completeness4/5

    The toolset covers core Spotify functionality well with only minor gaps. Notable missing operations include playlist/library management (saving/removing tracks), volume control, and seeking within tracks, but the provided tools enable basic listening workflows.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers