lastfm-mcp

mcp
Guvenlik Denetimi
Uyari
Health Gecti
  • License — License: MIT
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Community trust — 33 GitHub stars
Code Uyari
  • process.env — Environment variable access in .github/workflows/elezea-release-post.yml
  • network request — Outbound network request in .github/workflows/elezea-release-post.yml
Permissions Gecti
  • Permissions — No dangerous permissions requested
Purpose
This MCP server acts as a bridge between AI assistants (like Claude) and the Last.fm API, enabling users to query public music data, their personal listening history, and recommendations.

Security Assessment
Overall Risk: Medium. The server relies on a standard OAuth 2.0 flow to access a user's private Last.fm listening history, which is expected for this functionality, but requires user consent for sensitive data. It operates as a remote server on Cloudflare Workers, meaning it does not run locally or execute arbitrary shell commands on your machine. A code scan flagged outbound network requests and environment variable usage, but these are safely isolated within an automated GitHub Actions workflow for releases, not in the core application logic. There are no hardcoded secrets, and the tool does not request dangerous local system permissions.

Quality Assessment
The project appears to be actively maintained with recent repository updates. It is backed by a permissive MIT license, making it highly accessible for developers. It shows solid community trust for a niche integration, having earned 33 GitHub stars. The documentation is clean, clearly outlining available tools, authentication requirements, and setup instructions across multiple AI clients.

Verdict
Safe to use.
SUMMARY

An MCP server that provides seamless access to a user's Last.fm listening data and music information via AI assistants like Claude.

README.md

Last.fm MCP Server

A Model Context Protocol (MCP) server for Last.fm. Gives AI assistants access to your listening history, music discovery, and detailed track/artist/album information.

Runs on Cloudflare Workers with OAuth 2.0 authentication. Public tools (track info, artist info, similar artists) work without signing in -- connect your Last.fm account to access personal listening data.

Quick start

Claude.ai / Claude Desktop

  1. Open Settings -> Connectors -> Add Custom Connector
  2. Enter https://lastfm-mcp.com/mcp
  3. Sign in to Last.fm when prompted

Claude Code

claude mcp add --transport http lastfm "https://lastfm-mcp.com/mcp"

Windsurf

Add to ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "lastfm": {
      "serverUrl": "https://lastfm-mcp.com/mcp"
    }
  }
}

Other MCP clients

For clients that don't support remote servers directly (Continue.dev, Zed, etc.), use mcp-remote:

{
  "mcpServers": {
    "lastfm": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://lastfm-mcp.com/mcp"]
    }
  }
}

MCP Inspector

npx @modelcontextprotocol/inspector https://lastfm-mcp.com/mcp

Authentication

The server uses OAuth 2.0. When you connect from a supported client, your browser opens to Last.fm to authorize access. Tokens persist across sessions.

Public tools work without signing in. You only need to connect your account for personal listening data.

Available tools

Public tools

Tool Description
get_track_info Detailed information about a track
get_artist_info Artist information and bio
get_album_info Album details and track listing
get_similar_artists Artists similar to a given artist
get_similar_tracks Tracks similar to a given track
ping Test connectivity
server_info Server status and capabilities
lastfm_auth_status Check authentication status

Personal tools (requires sign-in)

Tool Description
get_recent_tracks Recent listening history (paginated)
get_top_artists Top artists by time period
get_top_albums Top albums by time period
get_loved_tracks Loved/favorited tracks
get_user_info Last.fm profile information
get_listening_stats Listening statistics
get_music_recommendations Personalized recommendations

Temporal queries (requires sign-in)

Tool Description
get_weekly_chart_list Available historical time periods
get_weekly_artist_chart Artist charts for a specific time period
get_weekly_track_chart Track charts for a specific time period

Good for questions like "when did I start listening to Led Zeppelin?" or "what was I into last March?"

Resources

The server exposes 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

Prompts

Prompt Description Arguments
listening_insights Analyze listening habits and patterns username, period?
music_discovery Discover music based on listening history username, genre?
track_analysis Detailed analysis of a track artist, track
album_analysis Detailed analysis of an album artist, album
artist_analysis Detailed analysis of an artist artist
listening_habits Summarize listening habits username, timeframe?

Development

Prerequisites

Local setup

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

Create .dev.vars:

LASTFM_API_KEY=your_api_key
LASTFM_SHARED_SECRET=your_shared_secret
JWT_SECRET=your_jwt_secret
npm run dev

Test with the inspector:

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

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:

npm run deploy:prod

Testing

npm test
npm run typecheck
npm run lint

Architecture

  • Runtime: Cloudflare Workers
  • Protocol: MCP (streamable HTTP)
  • Auth: OAuth 2.0 (RFC 9728)
  • Storage: Cloudflare KV for sessions, tokens, and caching
  • API: Last.fm Web API v2.0

Endpoints

Endpoint Purpose
/mcp MCP JSON-RPC endpoint
/authorize OAuth 2.0 authorization
/.well-known/oauth-authorization-server OAuth server metadata
/.well-known/oauth-protected-resource OAuth resource metadata

Contributing

  1. Fork the repo
  2. Create a feature branch
  3. Commit your changes
  4. Open a pull request

License

MIT

Yorumlar (0)

Sonuc bulunamadi