@striderlabs/mcp-spotify
MCP server for Spotify that lets AI agents search music, control playback, and manage playlists via the Spotify Web API.
README
@striderlabs/mcp-spotify
MCP server for Spotify — let AI agents search music, control playback, and manage playlists via the Spotify Web API.
Built by Strider Labs.
Features
- Search — Find tracks, artists, albums, and playlists
- Playlists — View, create, and edit your playlists
- Playback Control — Play, pause, skip, go back, set volume
- Multi-device — List and switch between Spotify Connect devices
- OAuth 2.0 — Secure authorization with PKCE (no client secret needed)
- Token persistence — Tokens stored locally, auto-refreshed
Setup
1. Create a Spotify App
- Go to the Spotify Developer Dashboard
- Click Create App
- Set Redirect URI to:
http://localhost:8888/callback - Copy your Client ID
2. Install
npx @striderlabs/mcp-spotify
Or install globally:
npm install -g @striderlabs/mcp-spotify
3. Configure Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"spotify": {
"command": "npx",
"args": ["-y", "@striderlabs/mcp-spotify"],
"env": {
"SPOTIFY_CLIENT_ID": "your_client_id_here"
}
}
}
}
4. Authenticate
In Claude, call the auth tool once:
spotify_auth
A browser window will open for you to authorize access. After approving, tokens are saved locally at ~/.striderlabs/spotify/tokens.json and auto-refreshed.
Environment Variables
| Variable | Required | Description |
|---|---|---|
SPOTIFY_CLIENT_ID |
Yes | Your Spotify app's Client ID |
Tools
Authentication
| Tool | Description |
|---|---|
spotify_status |
Check connection status and logged-in account |
spotify_auth |
Authorize via browser (OAuth 2.0 PKCE) |
spotify_logout |
Clear stored tokens |
Search
| Tool | Parameters | Description |
|---|---|---|
search_tracks |
query, limit? |
Search for songs |
search_artists |
query, limit? |
Search for artists |
search_albums |
query, limit? |
Search for albums |
search_playlists |
query, limit? |
Search for playlists |
Playlists
| Tool | Parameters | Description |
|---|---|---|
get_playlists |
limit? |
Get your playlists |
create_playlist |
name, description?, public? |
Create a new playlist |
add_to_playlist |
playlistId, uris[], position? |
Add tracks |
remove_from_playlist |
playlistId, uris[] |
Remove tracks |
Playback
| Tool | Parameters | Description |
|---|---|---|
get_currently_playing |
— | Current track, progress, device |
play |
deviceId?, contextUri?, uris?[], offsetPosition?, positionMs? |
Start/resume playback |
pause |
deviceId? |
Pause playback |
next_track |
deviceId? |
Skip to next track |
previous_track |
deviceId? |
Go to previous track |
set_volume |
volumePercent, deviceId? |
Set volume (0–100) |
get_devices |
— | List Spotify Connect devices |
transfer_playback |
deviceId, play? |
Switch playback device |
Example Workflow
1. spotify_status → check if authenticated
2. spotify_auth → open browser to authorize (first time)
3. search_tracks query="Bohemian Rhapsody"
4. get_devices → list available devices
5. play uris=["spotify:track:..."] deviceId="..."
6. get_currently_playing → see what's playing
7. set_volume volumePercent=70
8. next_track → skip to next
9. get_playlists → see your playlists
10. create_playlist name="AI Picks"
11. add_to_playlist playlistId="..." uris=["spotify:track:..."]
Requirements
- Node.js 18+
- Spotify account (Free or Premium)
- Spotify Premium required for: volume control, playback control
Technical Details
- Protocol: Model Context Protocol (MCP) over stdio
- Auth: OAuth 2.0 Authorization Code with PKCE
- API: Spotify Web API v1
- Token storage:
~/.striderlabs/spotify/tokens.json - Browser automation: Playwright (for OAuth browser launch)
License
MIT — Strider Labs
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。