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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.