SpotifyScraper MCP
A Python library and MCP server that give an agent public Spotify data, lyrics and transcripts with no API key
- 322 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The server calls the external Spotify service and parses its responses, with no official access guarantee
- The sp_dc cookie, if you set it, grants sign-in to your Spotify account and sits in the environment as a secret
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add mcp/spotifyscraperDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The server calls the external Spotify service and parses its responses, with no official access guarantee
- The sp_dc cookie, if you set it, grants sign-in to your Spotify account and sits in the environment as a secret
This is third-party code. Review the repository files before installing.
What it does
SpotifyScraper is a Python library that reads the public Spotify catalog: music, playlists and podcasts. It gets an anonymous token from Spotify's embed pages and calls the same JSON endpoints the web player uses. No app registration or API key is needed. The `spotifyscraper-mcp` server brings that data to Claude and other clients. Tools such as `get_track` and `get_album` return structured JSON, `search` queries the catalog, and batch versions fetch many IDs in one call. Separate tools return charts, related artists and cover colors. If you put your own `sp_dc` cookie into the `SPOTIFY_SP_DC` variable, tools that require a login switch on: lyrics, podcast transcripts, Canvas and account data. The server runs over stdio for desktop clients, over streamable-http and over SSE. Besides tools, it exposes resources such as `spotify://track/{id}` and three prompts: `describe_album`, `playlist_blurb` and `summarize_episode`.
Who it is for. For developers and researchers who need Spotify metadata, lyrics and transcripts in Claude or in their own Python script.
Good fit when
- You need a playlist's track list or an artist's discography
- You need a podcast episode transcript so the agent can summarize it
- You need an album's cover colors to pick a theme for a page or a release poster
- You need data for dozens of IDs in one request through the batch tools
- A Python project needs typed models and a sync or async client
Not a fit when
- You need to control playback or the queue, or write to an account: SpotifyScraper only reads public data
- You need your private library or listening recommendations: the official API fits those
- You need audio-features: Spotify removed that data from every tool
- You do not want to expose your account cookie but need lyrics or transcripts
Example request
Take this Spotify playlist, list the tracks with artists and duration, and find three related artists for the first track.MCP
- Transport
- stdio, http, sse
- Authentication
- not required
Environment variables
SPOTIFY_SP_DCsecret- The sp_dc cookie of your Spotify account for lyrics, transcripts, Canvas, credits and account data
Limitations
The project is unofficial and reads from the same addresses as the web player, so Spotify gives it no access guarantee. Data is read-only and playback cannot be controlled. The audio-features data cannot be restored: Spotify removed it entirely.
Lyrics, transcripts, Canvas, credits and account details need the `sp_dc` cookie from your account, which should be stored like a password. Python 3.10 or newer is required. Whether Spotify itself is reachable from Russia was not checked for this card.
How to disable. Remove the spotifyscraper entry from your MCP client config and, if you like, run `pip uninstall spotifyscraper`. If you set a cookie, delete `SPOTIFY_SP_DC` from the environment.
FAQ
How do I connect SpotifyScraper to Claude Desktop?
Install the package with `pip install "spotifyscraper[mcp]"` and add a server with the command `spotifyscraper-mcp` to `claude_desktop_config.json`. The `SPOTIFY_SP_DC` variable in the `env` block is needed only for login-based tools.
Do I need a Spotify API key?
No. The library gets an anonymous token from the embed pages and reads public data without an app registration.
How is SpotifyScraper different from spotipy?
spotipy uses the official Web API: it needs keys and OAuth, but it can write to an account and read private data. SpotifyScraper reads public data without keys, offers both sync and async modes and provides an MCP server.
How do I run the server in a container?
The `ghcr.io/aliakhtari78/spotifyscraper` image listens on port 8000 over HTTP by default. `docker run -p 8000:8000 ghcr.io/aliakhtari78/spotifyscraper` starts it, and the cookie is passed with `-e SPOTIFY_SP_DC`.
What do the tools return without a cookie?
The Canvas, credits, user, lyrics, transcript and account tools say in the reply that they need the `SPOTIFY_SP_DC` variable. The other tools work without it.
Discussion
No questions or reviews yet.
Related
MCP serversA Spotify MCP server: the agent searches music, controls playback, queue and volume, and builds and edits playlists and the library
Yandex Music MCP server with genre analysis
Yandex Music MCP Server
An unofficial Yandex Music MCP server: likes, genre analysis, search and playlist management over HTTP or stdio
MCP Music Forge: track download and processing
MCP Music Forge
A Redis-backed queue MCP server that downloads tracks from SoundCloud, YouTube, Yandex Music and Spotify, transcodes them and tags them with cover art
Yandex Music MCP for taste analysis
Yandex Music MCP
A single-file, zero-install Yandex Music MCP server via uv: likes, playlists, search and taste analysis
YouTube MCP (Zubeid)
Zubeid YouTube MCP Server
YouTube MCP on a Data API key: an agent searches videos and channels with a subscriber-count filter and reads playlists, statistics and transcripts
Yandex Music MCP server with a native macOS player
yandex-music-mcp
A browser-free Yandex Music MCP server: the agent queues a playlist, a local daemon plays it via mpv with Now Playing in Control Center
Comparison with similar tools
Entries that share the main search query, and how they differ.
| Entry | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| SpotifyScraper (this entry) | no | not required | 322 | |
| Spotify MCP Server | no | OAuth | 490 | controls playback, the queue and playlists through the official API, while SpotifyScraper reads public data with no keys |
| MCP Music Forge: track download and processing | no | key is optional | 5 | downloads and transcodes tracks from several services through a queue, whereas SpotifyScraper returns metadata only |
README in short
Version 3 is a ground-up rewrite for reliability and a clean API. The author compares the library with spotipy, shows sync and async client code and links an online demo. The repository is maintained with Claude Code.