Spotify MCP Server
Enables interaction with Spotify's music catalog through natural language conversations. Search for tracks and artists, get recommendations, explore playlists, and browse artist discographies using the Spotify Web API.
README
Spotify MCP Server
A Micro-Context Protocol (MCP) server that provides access to Spotify's music data through the Spotify Web API. Search for tracks, artists, and get top tracks from any artist - all through natural language conversations.
🎵 Features
- Search Tracks: Find songs by name, artist, or lyrics
- Search Artists: Discover artists and get their information
- Artist Top Tracks: Get the most popular tracks for any artist
Note: The Recommendations API is no longer available for new Spotify apps as of November 27, 2024. See Spotify's announcement for more details.
🚀 Quick Start
Prerequisites
- Python 3.8+
- Spotify Developer Account
- Spotify App credentials (Client ID and Client Secret)
Local Development
-
Clone and navigate to the repository:
git clone <your-repo-url> cd mcp-spotify -
Create a virtual environment:
python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate -
Install dependencies:
pip install -r requirements.txt -
Set up Spotify API credentials:
export SPOTIFY_CLIENT_ID="your_client_id" export SPOTIFY_CLIENT_SECRET="your_client_secret" -
Run the server:
python src/server.py
The server will start on http://localhost:8000 with the MCP endpoint at http://localhost:8000/mcp.
🔑 Getting Spotify API Credentials
- Go to Spotify Developer Dashboard
- Log in with your Spotify account
- Click "Create App"
- Fill in the app details:
- App name:
Your MCP Server(or any name you prefer) - App description:
MCP server for Spotify integration - Website:
https://spotify-mcp.onrender.com(use your deployed URL) - Redirect URI:
https://spotify-mcp.onrender.com(use your deployed URL)
- App name:
- Select "Web API" when asked about APIs/SDKs
- Click "Save"
- Copy your
Client IDandClient Secret
Note: Use your deployed Render URL (not localhost) for the redirect URI since Spotify requires HTTPS for security.
🚢 Deployment
Deploy to Render
Steps:
- Click the "Deploy to Render" button below (or go to render.com and sign up/login)
- Connect your GitHub account to Render (if you haven't already)
- Create a new Web Service:
- Connect this repository
- Name:
spotify-mcp - Environment:
Python 3 - Plan:
Free - Build Command:
pip install -r requirements.txt - Start Command:
python src/server.py
- Set environment variables:
- Go to your Render service dashboard
- Click on "Environment" tab
- Add:
SPOTIFY_CLIENT_ID=your_client_idSPOTIFY_CLIENT_SECRET=your_client_secret
- Click "Save Changes"
- Deploy!
Note: On Render's free tier, services go idle after ~15 minutes of inactivity and may require a manual "Deploy" to wake or to pick up the latest commit. Unlike Vercel, pushes do not auto-deploy by default.
Your server will be available at https://spotify-mcp.onrender.com/mcp
🎯 Poke Integration
- Go to poke.com/settings/connections
- Add the MCP URL:
https://spotify-mcp.onrender.com/mcp - Give it a name like "Spotify"
- Try: "Can you use the Spotify MCP to search tracks for 'Bohemian Rhapsody'?"
References
- Based on the Interaction MCP server template: MCP Server Template
- Discovered via Interaction’s HackMIT challenge: Interaction HackMIT Challenge
🛠️ Available Tools
search_tracks(query, limit=10)
Search for tracks on Spotify.
Parameters:
query(string): Search query (song name, artist, lyrics, etc.)limit(int, optional): Number of results to return (1-50, default: 10)
Example:
search_tracks("Bohemian Rhapsody", 5)
search_artists(query, limit=10)
Search for artists on Spotify.
Parameters:
query(string): Search query (artist name, genre, etc.)limit(int, optional): Number of results to return (1-50, default: 10)
Example:
search_artists("Queen", 3)
get_artist_top_tracks(artist_id, market="US")
Get the top tracks for a specific artist.
Parameters:
artist_id(string): Spotify artist IDmarket(string, optional): Market code (default: "US")
Example:
get_artist_top_tracks("1dfeR4HaWDbWqFHLkxsg1d") # Queen's artist ID
🧪 Testing
Test the server locally:
# Test health endpoint
curl http://localhost:8000/
# Test MCP endpoint
curl -X POST http://localhost:8000/mcp \
-H "Content-Type: application/json" \
-d '{"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}}'
📝 Notes
- Rate Limiting: The Spotify API has rate limits. The server includes automatic token refresh.
- Authentication: Uses Spotify's Client Credentials flow (no user login required).
- Data Format: All responses are in JSON format for easy integration.
- Error Handling: Comprehensive error handling with descriptive error messages.
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。