Spotify MCP Server
Enables AI assistants to control Spotify playback, search for music, manage playlists, and interact with your Spotify library through natural language commands.
README
<div align="center" style="display: flex; align-items: center; justify-content: center; gap: 10px;"> <img src="https://upload.wikimedia.org/wikipedia/commons/8/84/Spotify_icon.svg" width="30" height="30"> <h1>Spotify MCP Server</h1> </div>
A lightweight Model Context Protocol (MCP) server that enables AI assistants like Cursor & Claude to control Spotify playback and manage playlists.
<details> <summary>Contents</summary>
- Example Interactions
- Tools
- Setup
- Integrating with Claude Desktop, Cursor, and VsCode (Cline) </details>
Example Interactions
- "Play Elvis's first song"
- "Create a Taylor Swift / Slipknot fusion playlist"
- "Copy all the techno tracks from my workout playlist to my work playlist"
Tools
Read Operations
-
searchSpotify
- Description: Search for tracks, albums, artists, or playlists on Spotify
- Parameters:
query(string): The search termtype(string): Type of item to search for (track, album, artist, playlist)limit(number, optional): Maximum number of results to return (10-50)
- Returns: List of matching items with their IDs, names, and additional details
- Example:
searchSpotify("bohemian rhapsody", "track", 20)
-
getNowPlaying
- Description: Get information about the currently playing track on Spotify
- Parameters: None
- Returns: Object containing track name, artist, album, playback progress, duration, and playback state
- Example:
getNowPlaying()
-
getMyPlaylists
- Description: Get a list of the current user's playlists on Spotify
- Parameters:
limit(number, optional): Maximum number of playlists to return (default: 20)offset(number, optional): Index of the first playlist to return (default: 0)
- Returns: Array of playlists with their IDs, names, track counts, and public status
- Example:
getMyPlaylists(10, 0)
-
getPlaylistTracks
- Description: Get a list of tracks in a specific Spotify playlist
- Parameters:
playlistId(string): The Spotify ID of the playlistlimit(number, optional): Maximum number of tracks to return (default: 100)offset(number, optional): Index of the first track to return (default: 0)
- Returns: Array of tracks with their IDs, names, artists, album, duration, and added date
- Example:
getPlaylistTracks("37i9dQZEVXcJZyENOWUFo7")
-
getRecentlyPlayed
- Description: Retrieves a list of recently played tracks from Spotify.
- Parameters:
limit(number, optional): A number specifying the maximum number of tracks to return.
- Returns: If tracks are found it returns a formatted list of recently played tracks else a message stating: "You don't have any recently played tracks on Spotify".
- Example:
getRecentlyPlayed({ limit: 10 })
-
getUsersSavedTracks
- Description: Get a list of tracks saved in the user's "Liked Songs" library
- Parameters:
limit(number, optional): Maximum number of tracks to return (1-50, default: 50)offset(number, optional): Offset for pagination (0-based index, default: 0)
- Returns: Formatted list of saved tracks with track names, artists, duration, track IDs, and when they were added to Liked Songs. Shows pagination info (e.g., "1-20 of 150").
- Example:
getUsersSavedTracks({ limit: 20, offset: 0 })
Play / Create Operations
-
playMusic
- Description: Start playing a track, album, artist, or playlist on Spotify
- Parameters:
uri(string, optional): Spotify URI of the item to play (overrides type and id)type(string, optional): Type of item to play (track, album, artist, playlist)id(string, optional): Spotify ID of the item to playdeviceId(string, optional): ID of the device to play on
- Returns: Success status
- Example:
playMusic({ uri: "spotify:track:6rqhFgbbKwnb9MLmUQDhG6" }) - Alternative:
playMusic({ type: "track", id: "6rqhFgbbKwnb9MLmUQDhG6" })
-
pausePlayback
- Description: Pause the currently playing track on Spotify
- Parameters:
deviceId(string, optional): ID of the device to pause
- Returns: Success status
- Example:
pausePlayback()
-
skipToNext
- Description: Skip to the next track in the current playback queue
- Parameters:
deviceId(string, optional): ID of the device
- Returns: Success status
- Example:
skipToNext()
-
skipToPrevious
- Description: Skip to the previous track in the current playback queue
- Parameters:
deviceId(string, optional): ID of the device
- Returns: Success status
- Example:
skipToPrevious()
-
createPlaylist
- Description: Create a new playlist on Spotify
- Parameters:
name(string): Name for the new playlistdescription(string, optional): Description for the playlistpublic(boolean, optional): Whether the playlist should be public (default: false)
- Returns: Object with the new playlist's ID and URL
- Example:
createPlaylist({ name: "Workout Mix", description: "Songs to get pumped up", public: false })
-
addTracksToPlaylist
- Description: Add tracks to an existing Spotify playlist
- Parameters:
playlistId(string): ID of the playlisttrackUris(array): Array of track URIs or IDs to addposition(number, optional): Position to insert tracks
- Returns: Success status and snapshot ID
- Example:
addTracksToPlaylist({ playlistId: "3cEYpjA9oz9GiPac4AsH4n", trackUris: ["spotify:track:4iV5W9uYEdYUVa79Axb7Rh"] })
-
addToQueue
- Description: Adds a track, album, artist or playlist to the current playback queue
-
- Parameters:
uri(string, optional): Spotify URI of the item to add to queue (overrides type and id)type(string, optional): Type of item to queue (track, album, artist, playlist)id(string, optional): Spotify ID of the item to queuedeviceId(string, optional): ID of the device to queue on
- Returns: Success status
- Example:
addToQueue({ uri: "spotify:track:6rqhFgbbKwnb9MLmUQDhG6" }) - Alternative:
addToQueue({ type: "track", id: "6rqhFgbbKwnb9MLmUQDhG6" })
Album Operations
-
getAlbums
- Description: Get detailed information about one or more albums by their Spotify IDs
- Parameters:
albumIds(string|array): A single album ID or array of album IDs (max 20)
- Returns: Album details including name, artists, release date, type, total tracks, and ID. For single album returns detailed view, for multiple albums returns summary list.
- Example:
getAlbums("4aawyAB9vmqN3uQ7FjRGTy")orgetAlbums(["4aawyAB9vmqN3uQ7FjRGTy", "1DFixLWuPkv3KT3TnV35m3"])
-
getAlbumTracks
- Description: Get tracks from a specific album with pagination support
- Parameters:
albumId(string): The Spotify ID of the albumlimit(number, optional): Maximum number of tracks to return (1-50)offset(number, optional): Offset for pagination (0-based index)
- Returns: List of tracks from the album with track names, artists, duration, and IDs. Shows pagination info.
- Example:
getAlbumTracks("4aawyAB9vmqN3uQ7FjRGTy", 10, 0)
-
saveOrRemoveAlbumForUser
- Description: Save or remove albums from the user's "Your Music" library
- Parameters:
albumIds(array): Array of Spotify album IDs (max 20)action(string): Action to perform: "save" or "remove"
- Returns: Success status with confirmation message
- Example:
saveOrRemoveAlbumForUser(["4aawyAB9vmqN3uQ7FjRGTy"], "save")
-
checkUsersSavedAlbums
- Description: Check if albums are saved in the user's "Your Music" library
- Parameters:
albumIds(array): Array of Spotify album IDs to check (max 20)
- Returns: Status of each album (saved or not saved)
- Example:
checkUsersSavedAlbums(["4aawyAB9vmqN3uQ7FjRGTy", "1DFixLWuPkv3KT3TnV35m3"])
Setup
Prerequisites
- Node.js v16+
- A Spotify Premium account
- A registered Spotify Developer application
Installation
git clone https://github.com/marcelmarais/spotify-mcp-server.git
cd spotify-mcp-server
npm install
npm run build
Creating a Spotify Developer Application
- Go to the Spotify Developer Dashboard
- Log in with your Spotify account
- Click the "Create an App" button
- Fill in the app name and description
- Accept the Terms of Service and click "Create"
- In your new app's dashboard, you'll see your Client ID
- Click "Show Client Secret" to reveal your Client Secret
- Click "Edit Settings" and add a Redirect URI (e.g.,
http://127.0.0.1:8888/callback) - Save your changes
Spotify API Configuration
Create a spotify-config.json file in the project root (you can copy and modify the provided example):
# Copy the example config file
cp spotify-config.example.json spotify-config.json
Then edit the file with your credentials:
{
"clientId": "your-client-id",
"clientSecret": "your-client-secret",
"redirectUri": "http://127.0.0.1:8888/callback"
}
Authentication Process
The Spotify API uses OAuth 2.0 for authentication. Follow these steps to authenticate your application:
- Run the authentication script:
npm run auth
-
The script will generate an authorization URL. Open this URL in your web browser.
-
You'll be prompted to log in to Spotify and authorize your application.
-
After authorization, Spotify will redirect you to your specified redirect URI with a code parameter in the URL.
-
The authentication script will automatically exchange this code for access and refresh tokens.
-
These tokens will be saved to your
spotify-config.jsonfile, which will now look something like:
{
"clientId": "your-client-id",
"clientSecret": "your-client-secret",
"redirectUri": "http://localhost:8888/callback",
"accessToken": "BQAi9Pn...kKQ",
"refreshToken": "AQDQcj...7w",
"expiresAt": 1677889354671
}
- The server will automatically refresh the access token when needed, using the refresh token.
Integrating with Claude Desktop, Cursor, and VsCode Via Cline model extension
To use your MCP server with Claude Desktop, add it to your Claude configuration:
{
"mcpServers": {
"spotify": {
"command": "node",
"args": ["spotify-mcp-server/build/index.js"]
}
}
}
For Cursor, go to the MCP tab in Cursor Settings (command + shift + J). Add a server with this command:
node path/to/spotify-mcp-server/build/index.js
To set up your MCP correctly with Cline ensure you have the following file configuration set cline_mcp_settings.json:
{
"mcpServers": {
"spotify": {
"command": "node",
"args": ["~/../spotify-mcp-server/build/index.js"],
"autoApprove": ["getListeningHistory", "getNowPlaying"]
}
}
}
You can add additional tools to the auto approval array to run the tools without intervention.
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。