Genius is two things at once: an official API and a large body of community writing. Annotations arrive tagged with a trust level, so an agent can tell an artist-verified explanation from an anonymous guess instead of flattening both into 'the internet says'.
An MCP server over Genius.com, using the official Genius API with your access token and the `lyricsgenius` Python library for endpoints the official API does not cover.
- Songs and artists searched by name
- Full song metadata — title, album, release date, lyrics state and Genius's editorial description
- Artist profiles with bio, follower count and verification status
- Line-level annotations explaining specific lyric fragments, each carrying a trust level so a model knows how much weight to give it
- A single annotation read in detail
- Song relationships — what a track samples, interpolates, covers or remixes, and what later sampled it
- Credits: writers, producers, featured artists and custom roles such as mixing engineer, studio and label
- The questions and answers attached to a song
A Genius API access token. Runs with Python or from the included Docker image, in either transport mode. Worth knowing which half you are on: the tools built on `lyricsgenius` reach Genius's undocumented public API, which is not part of the official contract and can change without notice — those are the results that will break first.