
Connects Claude to Genius.com's lyrics database through three focused tools: pull artist bios and metadata, list an artist's songs sorted by popularity or release date, and fetch individual annotations (the community-contributed explanations Genius is known for). Runs as a streamable HTTP endpoint through Pipeworx's gateway, which means no local setup or API key juggling. Useful when you need structured music metadata or want to analyze song meanings and cultural context that the Genius community has annotated. You can call tools directly or use the ask_pipeworx wrapper to query in plain English and let it route to the right endpoint.
Genius MCP — song / artist / album metadata, search, and Genius annotation descriptions. Lyric text is not returned by the Genius API (licensing) — this pack returns titles, IDs, stats, Genius page URLs, and "about" descriptions.
Part of Pipeworx — an MCP gateway connecting AI agents to 1476+ live data sources.
search(query, limit?) — keyword search; returns song metadata hitsget_song(id) — song metadata (title, artist, album, release, pageviews, about)get_artist(id) — artist metadata (name, followers, alternate names, about)artist_songs(artist_id, limit?) — songs by an artist, ranked by popularity_apiKey is optional on every tool — omit it to use the platform key.
_apiKey is omitted._apiKey=<token> after registering a free Client Access Token
at https://genius.com/api-clients.Sent as Authorization: Bearer <token> on every request.
https://api.genius.com — Bearer access token.
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"genius": {
"url": "https://gateway.pipeworx.io/genius/mcp"
}
}
}
tools/list at https://gateway.pipeworx.io/genius/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}
Both URLs reach the same gateway and the same 1476+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Genius data" })
The gateway picks the right tool and fills the arguments automatically.
MIT