Spotify MCP Server

Spotify MCP Server

Controls Spotify playback through Claude using the Model Context Protocol. Supports playback control, search, library management, and local favorites.

Category
访问服务器

README

Spotify MCP Server

Control Spotify playback through Claude using the Model Context Protocol (MCP).

Uses PKCE authentication - just install and authorize your Spotify account.

Note: The bundled client ID works for playback control and reading data. For write operations (adding to playlists, saving to library), you'll need to set up your own Spotify app.

Quick Start

1. Install

git clone https://github.com/panuhen/spotify-mcp.git ~/spotify-mcp
cd ~/spotify-mcp
python -m venv .venv
.venv/bin/pip install -e .

2. First Run - Authenticate

Run once to authorize with your Spotify account:

~/spotify-mcp/.venv/bin/spotify-mcp

This opens your browser for Spotify login. After authorizing, the token is cached at ~/.spotify-mcp-token.

3. Add to Claude Code

Add to ~/.mcp.json:

{
  "mcpServers": {
    "spotify": {
      "command": "/home/YOUR_USER/spotify-mcp/.venv/bin/spotify-mcp"
    }
  }
}

Then enable in ~/.claude/settings.local.json:

{
  "enabledMcpjsonServers": ["spotify"]
}

Restart Claude Code and you're ready!

Available Tools

Playback Control

  • play - Resume or play specific track/album/playlist
  • pause - Pause playback
  • next - Skip to next track
  • previous - Go to previous track
  • seek - Seek to position in track
  • set_volume - Set volume (0-100)
  • shuffle - Toggle shuffle mode
  • repeat - Set repeat mode (off/track/context)

Information

  • get_current_track - Get currently playing track info
  • get_playback_state - Get full playback state
  • get_queue - Get upcoming tracks
  • get_devices - List available devices

Search & Library

  • search - Search for tracks, albums, artists, playlists
  • add_to_queue - Add track to queue
  • get_playlists - List your playlists
  • get_playlist_tracks - Get tracks from a playlist
  • add_to_playlist - Add tracks to a playlist (requires own app)
  • save_tracks - Save tracks to your library (requires own app)
  • remove_saved_tracks - Remove tracks from library (requires own app)
  • get_saved_tracks - Get your liked tracks

Local Favorites

No Spotify API permissions needed - stored locally in ~/.spotify-mcp-favorites.json:

  • favorite_current - Add currently playing track to favorites
  • get_favorites - List all favorited tracks
  • remove_favorite - Remove a track from favorites
  • play_favorites - Play random favorite or queue all favorites
  • clear_favorites - Clear all favorites

Usage Examples

Once configured, you can ask Claude:

  • "What song is currently playing?"
  • "Pause the music"
  • "Play the next track"
  • "Search for 'Bohemian Rhapsody' and add it to the queue"
  • "Set the volume to 50%"
  • "Turn on shuffle"
  • "Show my playlists"

Setup Your Own Spotify App

Required for: add_to_playlist, save_tracks, remove_saved_tracks

The bundled client ID is in Spotify's Development Mode, which restricts write operations. To use all features:

  1. Create an app at https://developer.spotify.com/dashboard
  2. In your app settings, add redirect URI: http://127.0.0.1:8888/callback
  3. Copy your Client ID and add to ~/spotify-mcp/.env:
    SPOTIPY_CLIENT_ID=your_client_id_here
    
  4. Delete cached token and re-auth:
    rm ~/.spotify-mcp-token
    
  5. Restart the MCP server

Troubleshooting

"No active device" error

Make sure Spotify is open on at least one device (phone, desktop app, web player).

Authentication issues

Delete ~/.spotify-mcp-token and run spotify-mcp again to re-authenticate.

Token expired

The token auto-refreshes, but if issues persist, delete ~/.spotify-mcp-token and re-auth.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选