M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
S

Spotifyscraper

Community
Public Spotify metadata, lyrics and podcasts for LLM agents. No API key, read-only.
How to install ↓ Compare GitHub source repository ↗
Category
Other #64 of 230
Stars
★ 316 Very popular
Transport
stdio (local process)
Runtime
Python 3.10+ · Docker
Credentials
No credential needed
License
MIT
Last commit
61FMRS · C

SpotifyScraper provides a valuable keyless access to Spotify data for AI agents, but it relies on unofficial endpoints, posing breakage risk, and is suitable for non-critical read-only use cases.

Strongest · Maintenance 14/20 Weakest · Reliability 8/20

Reliability
8/20
Security and permissions
14/20
Maintenance
14/20
Documentation
13/20
Setup experience
12/20
Why each score
Reliability 8/20
The manifest is well-formed and internally consistent: name, package spotifyscraper 3.9.2, stdio transport, and one optional env var SPOTIFY_SP_DC all align; the README describes a coherent sync/async library with an mcp extra, so the happy path is plausible. However, no server source, tool definitions, or test files were supplied, so tool-list/behavior conformance cannot be verified statically; the claimed CI, daily canary, and 85% coverage floor are README assertions only. The server also rides undocumented Spotify web endpoints that the README itself admits can break at any time. Deducted for missing executable evidence and inherent endpoint fragility.
Security and permissions 14/20
The design follows least privilege: read-only public data with no write/delete/pay/remote-command operations; the only secret, SPOTIFY_SP_DC, is optional, marked isSecret, and per docs is sent only to Spotify and never logged; the response cache deliberately excludes token-bearing responses; the cookie is stored in an owner-only file or optionally the OS keyring; no install example contains real credentials. No malware, covert exfiltration, or fabricated-identity red lines were found. Deducted because the actual implementation of log redaction and cookie handling cannot be confirmed from the supplied source, and there is no independent vulnerability-disclosure channel.
Maintenance 14/20
Sustained maintenance is evident: MIT license, clear author ownership, versioning at 3.9.2 with a per-version shipped roadmap, and a described daily canary that auto-opens/closes breakage issues. Deducted because no security-response channel (e.g., SECURITY.md) is provided, no changelog is included in the material, and the CI, coverage, and SHA-pinned Actions claims are README assertions without supporting workflow/test files; responsiveness to the 8 open issues cannot be assessed.
Documentation 13/20
The README is layered and thorough: install extras, sync/async quickstarts, CLI, batch helpers, caching, search, lyrics, podcast transcripts, localization, browser login, legal notice, and a link to full docs. Deducted because MCP-specific documentation is thin — no client configuration examples (e.g., Claude Desktop JSON), no MCP tool list or parameter reference, no MCP troubleshooting or explicit limits; SPOTIFY_SP_DC auth is described but failure modes are not; rate-limit/anti-ban specifics are mentioned only at a high level.
Setup experience 12/20
The install path is clear and short: pip install spotifyscraper[mcp] on Python 3.10+, with a container image and an optional env var as alternatives; the manifest package identifier and version match PyPI. Deducted because the README shows no client configuration example for wiring the stdio server into a mainstream LLM host, so the registry/connection step is left to the user; per static calibration, real CI workflows plus committed tests covering the server's key paths were not among the supplied files, so the score stays below the 15 cap. Manifest/package alignment is plausible but unverified.

Static review · not runListed 2026-08-07

Read the FMRS scoring method →

Fit and risk

What it can accessUses the network

Best for

  • Developers needing quick, keyless access to public Spotify metadata.
  • LLM applications that want to provide Spotify data to agents.
  • Personal projects needing music metadata for audio content.
  • Researchers looking to add music search to AI applications.

Not for

  • Applications that need to write to a user's Spotify account or access private/library data.
  • Use cases requiring market-accurate availability or region-specific data.
  • Production-critical applications where breakage risk is unacceptable.

Required permissions

  • No authentication is required by default.
  • Optionally, SPOTIFY_SP_DC cookie is required to enable lyrics, transcripts, and account tools. This cookie is secret.

Risks and side effects

  • This relies on Spotify's public private endpoints, which can change without notice, causing breakage.
  • There is risk of Spotify banning, but the library includes anti-ban measures.
  • This is unofficial and may violate Spotify's terms of service; use for educational or personal purposes.

Setup

Before you start

Runtime：Python 3.10+ · Docker

SPOTIFY_SP_DC optionalsecret Optional Spotify login cookie (sp_dc) that unlocks authenticated tools (lyrics, transcripts, account info); obtain it from a logged-in browser's Spotify cookies.

Install the Python package: pip install 'spotifyscraper[mcp]'. Then configure your MCP client to run spotifyscraper-mcp. Optionally, set the SPOTIFY_SP_DC environment variable to enable authenticated tools.

Check that it works

Check that the spotifyscraper MCP tools (e.g. get_track, get_track_visuals) appear in the client's tool list, then ask for a track's name and artists to confirm the connection works.

Troubleshooting

  1. Ensure Python version is >=3.10.
  2. Check if SPOTIFY_SP_DC cookie is valid and not expired.
  3. Verify network connectivity and accessibility of Spotify.
  4. Reinstall the package to get the latest version.

Things to try

Once connected, you can ask your AI assistant things like:

  • Get the name, artists, and duration of track 4uLU6hMCjMI75M1A2tKUQC
  • Search daft punk and return the top 5 track and artist matches
  • List the tracks on album 6N9PS4QXF1D0OWPk0Sxtb4
  • Fetch the cover colors and preview for this track via get_track_visuals

Use cases

Fetch public Spotify track, album, artist, playlist, and podcast data without an API key.
Retrieve lyrics and podcast transcripts in AI applications.
Build Spotify metadata searches for research.
Download cover art and preview clips.

Overview

SpotifyScraper is an MCP server that extracts tracks, albums, artists, playlists, podcasts, and lyrics from Spotify's public web data. It does not require the official API or an API key, instead bootstrapping an anonymous token from Spotify's public embed pages and reading the same JSON endpoints the web player uses. It offers sync and async Python clients, typed immutable models, and an MCP server for easy access by AI agents like Claude. Optional authenticated features (lyrics, podcast transcripts) use your Spotify sp_dc cookie—no password or API key required.

Similar servers

BioMCP 75 · B

One binary. One grammar. Evidence from the biomedical sources you already trust.

★ 654 · Tools 11 Compare with this →
Compare with other MCP servers

Source revision 9cbf05aa4963 Data synced 2026-10-12 Read the FMRS scoring method