🎵 Last.fm MCP Server

A Model Context Protocol (MCP) server that provides seamless access to Last.fm listening data and music information via AI assistants like Claude.

A powerful, production-ready server that bridges AI assistants with Last.fm's comprehensive music database.

✨ Features

🎧 Personal Listening Data: Recent tracks, top artists, albums, loved tracks
🎵 Music Information: Detailed track, artist, and album information
🔍 Music Discovery: Similar artists/tracks, personalized recommendations
📊 Listening Statistics: Comprehensive stats and listening habits analysis
🔐 Secure Authentication: Last.fm Web Authentication with JWT sessions
⚡ Smart Caching: Intelligent caching with optimized TTLs for performance
🛡️ Rate Limiting: Built-in rate limiting respecting Last.fm API limits
🌐 Production Ready: Deployed on Cloudflare Workers with global edge and CI/CD

🚀 Quick Start

Using with Claude Code (Recommended)

The easiest way to get started:

claude mcp add --transport http lastfm https://lastfm-mcp-prod.rian-db8.workers.dev

That's it! Claude Code now supports HTTP transport natively, no additional tools needed.

Using with Claude Desktop

Recommended Method (Connectors UI):

Claude Desktop now supports remote MCP servers natively:

Open Claude Desktop
Go to Settings → Connectors
Click Add Connector
Enter the server URL: https://lastfm-mcp-prod.rian-db8.workers.dev
Click Add

That's it! No configuration files or command-line tools needed. The server will appear in your Connectors list and be ready to use.

Alternative Method (Configuration File):

For advanced users who prefer config files, add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):

{
	"mcpServers": {
		"lastfm": {
			"command": "npx",
			"args": ["-y", "mcp-remote", "https://lastfm-mcp-prod.rian-db8.workers.dev"]
		}
	}
}

💡 Note: The Connectors UI method is recommended as it's simpler and doesn't require any command-line tools.

Using with Other MCP Clients

This server works with any MCP client that supports Streamable HTTP transport:

Continue.dev (VS Code/JetBrains):

Add to your Continue config (~/.continue/config.json):

{
	"mcpServers": {
		"lastfm": {
			"command": "npx",
			"args": ["-y", "mcp-remote", "https://lastfm-mcp-prod.rian-db8.workers.dev"]
		}
	}
}

Zed Editor:

Add to your Zed settings:

{
	"context_servers": {
		"lastfm": {
			"command": "npx",
			"args": ["-y", "mcp-remote", "https://lastfm-mcp-prod.rian-db8.workers.dev"]
		}
	}
}

MCP Inspector (Testing):

Test the server directly:

npx @modelcontextprotocol/inspector https://lastfm-mcp-prod.rian-db8.workers.dev

Custom Implementation:

Use the MCP client SDK for your language:

TypeScript/JavaScript: @modelcontextprotocol/sdk
Python: mcp package
Server endpoint: https://lastfm-mcp-prod.rian-db8.workers.dev
Transport: Streamable HTTP (protocol version 2024-11-05 or 2025-06-18)

🐛 Platform-Specific Troubleshooting

If you get "spawn npx NOENT" error

For NixOS users:

{
	"mcpServers": {
		"lastfm": {
			"command": "/run/current-system/sw/bin/npx",
			"args": ["mcp-remote", "https://lastfm-mcp-prod.rian-db8.workers.dev/sse"],
			"env": {
				"PATH": "/run/current-system/sw/bin:$PATH"
			}
		}
	}
}

For other systems:

Find your npx path: which npx
Use the full path in your config:

{
	"command": "/usr/local/bin/npx", // Use your actual path
	"args": ["mcp-remote", "https://lastfm-mcp-prod.rian-db8.workers.dev/sse"]
}

🔑 Authentication Flow

Try any authenticated tool (like "Get my recent tracks")
Claude will provide a Last.fm authentication URL
Sign in with your Last.fm account and authorize the app
Return to Claude - you're now authenticated!
Enjoy access to your personal Last.fm data

🛠️ Available Tools

🔓 Public Tools (No Authentication Required)

Tool	Description
`get_track_info`	Get detailed information about any track
`get_artist_info`	Get detailed artist information and bio
`get_album_info`	Get album details and track listings
`get_similar_artists`	Find artists similar to a given artist
`get_similar_tracks`	Find tracks similar to a given track
`ping`	Test server connectivity
`server_info`	Get server status and capabilities
`auth_status`	Check your authentication status

🔐 Personal Tools (Authentication Required)

Tool	Description
`get_recent_tracks`	Your recent listening history (supports pagination)
`get_top_artists`	Your top artists by time period
`get_top_albums`	Your top albums by time period
`get_loved_tracks`	Your loved/favorite tracks
`get_user_info`	Your Last.fm profile information
`get_listening_stats`	Comprehensive listening statistics
`get_music_recommendations`	Personalized music recommendations

🕰️ Temporal Query Tools (Authentication Required)

Tool	Description
`get_weekly_chart_list`	Get available historical time periods for temporal analysis
`get_weekly_artist_chart`	Get artist listening data for specific time periods
`get_weekly_track_chart`	Get track listening data for specific time periods

Perfect for questions like:

"When did I start listening to Led Zeppelin?"
"What was I listening to in March 2023?"
"How has my music taste evolved over time?"

📚 MCP Resources

Access Last.fm data via standardized MCP resource URIs:

lastfm://user/{username}/recent          # Recent tracks
lastfm://user/{username}/top-artists     # Top artists
lastfm://user/{username}/top-albums      # Top albums
lastfm://user/{username}/loved           # Loved tracks
lastfm://user/{username}/profile         # User profile
lastfm://track/{artist}/{track}          # Track info
lastfm://artist/{artist}                 # Artist info
lastfm://album/{artist}/{album}          # Album info
lastfm://artist/{artist}/similar         # Similar artists
lastfm://track/{artist}/{track}/similar  # Similar tracks

🤖 MCP Prompts

Rich AI prompts for music analysis and discovery:

Prompt	Description	Arguments
`listening_insights`	Analyze user's listening habits and patterns	`username`, `period?`
`music_discovery`	Discover new music based on listening history	`username`, `genre?`
`track_analysis`	Get detailed analysis of a specific track	`artist`, `track`
`album_analysis`	Get detailed analysis of a specific album	`artist`, `album`
`artist_analysis`	Get detailed analysis of a specific artist	`artist`
`listening_habits`	Analyze and summarize user's listening habits	`username`, `timeframe?`

These prompts generate contextual messages that guide AI assistants to provide meaningful music insights using the available Last.fm tools and data.

🏗️ Development

Prerequisites

Node.js 18+
Cloudflare Workers account
Last.fm API credentials (Get them here)

Local Setup

Clone and install:

git clone https://github.com/rianvdm/lastfm-mcp.git
cd lastfm-mcp
npm install

Configure environment (.dev.vars):

LASTFM_API_KEY=your_api_key_here
LASTFM_SHARED_SECRET=your_shared_secret_here
JWT_SECRET=your_secure_jwt_secret

Start development server:
```
npm run dev
```

Connect with Claude Code (for interactive testing):

claude mcp add --transport http lastfm-local http://localhost:8787

Or test with MCP Inspector:

npx @modelcontextprotocol/inspector http://localhost:8787

Test with curl (for basic API testing):

curl -X POST http://localhost:8787 \
  -H "Content-Type: application/json" \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"get_track_info","arguments":{"artist":"The Beatles","track":"Yesterday"}}}'

🚀 Deployment

Set production secrets:

echo "your_api_key" | wrangler secret put LASTFM_API_KEY --env production
echo "your_shared_secret" | wrangler secret put LASTFM_SHARED_SECRET --env production
echo "your_jwt_secret" | wrangler secret put JWT_SECRET --env production

Deploy:
```
wrangler deploy --env production
```
Test production:
```
curl https://your-worker.workers.dev
```

📋 Example Usage

🎵 Public Music Data (No Authentication)

Get track information:

curl -X POST https://lastfm-mcp-prod.rian-db8.workers.dev \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_track_info",
      "arguments": {
        "artist": "Radiohead",
        "track": "Paranoid Android"
      }
    }
  }'

Find similar artists:

curl -X POST https://lastfm-mcp-prod.rian-db8.workers.dev \
  -H "Content-Type: application/json" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_similar_artists",
      "arguments": {
        "artist": "Pink Floyd",
        "limit": 10
      }
    }
  }'

🔐 Personal Data (Requires Authentication)

Get recent tracks with pagination:

curl -X POST https://lastfm-mcp-prod.rian-db8.workers.dev \
  -H "Content-Type: application/json" \
  -H "Cookie: session=your_session_token" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_recent_tracks",
      "arguments": {
        "username": "your_username",
        "limit": 500,
        "page": 2
      }
    }
  }'

🕰️ Temporal Queries

Get available historical periods:

curl -X POST https://lastfm-mcp-prod.rian-db8.workers.dev \
  -H "Content-Type: application/json" \
  -H "Cookie: session=your_session_token" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_weekly_chart_list",
      "arguments": {
        "username": "your_username"
      }
    }
  }'

Discover what you were listening to in a specific time period:

curl -X POST https://lastfm-mcp-prod.rian-db8.workers.dev \
  -H "Content-Type: application/json" \
  -H "Cookie: session=your_session_token" \
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_weekly_artist_chart",
      "arguments": {
        "username": "your_username",
        "from": 1577836800,
        "to": 1578441600
      }
    }
  }'

🤖 AI Assistant Examples

With Claude or other AI assistants, you can now ask natural language questions like:

"When did I start listening to Led Zeppelin?"
"What was I obsessed with in summer 2023?"
"Show me how my music taste has evolved over the years"
"Find artists similar to my current favorites"
"What tracks should I check out based on my listening history?"

🏗️ Architecture

🌐 Runtime: Cloudflare Workers (global edge deployment)
📡 Protocol: Model Context Protocol (MCP) 2024-11-05
🔐 Authentication: Last.fm Web Auth + JWT sessions
💾 Storage: Cloudflare KV (sessions, caching, rate limiting)
🎵 API: Last.fm Web API v2.0
⚡ Performance: Smart caching, rate limiting, retry logic

🧪 Testing

# Run tests
npm test

# Type checking
npm run typecheck

# Linting
npm run lint

# Build check
npm run build

🤝 Contributing

Fork the repository
Create a feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

📝 License

MIT License - see LICENSE file for details.

🙏 Acknowledgments

Last.fm for the comprehensive music API
Model Context Protocol for the MCP specification
Cloudflare Workers for the serverless runtime

🎵 Built with ❤️ for music lovers and AI enthusiasts