lyrics-mcp
This server writes original song lyrics from a creative brief and returns them formatted for music-generation models.
Provide a brief describing what the song is about; concrete imagery gives better results.
Get back a title and full lyrics with English section tags like [Verse], [Chorus], [Bridge], and [Outro].
Optionally specify language, genre, mood, and song structure; otherwise the model chooses sensible defaults.
Section tags stay English even when lyrics are written in another language.
Output is ready to paste directly into AI music generation tools.
Configure the model, fallback model, API base URL, and per-process request rate through environment variables.
Runs locally on your machine using your own Anthropic API key; no hosted service is involved.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@lyrics-mcp Write a wistful indie folk song about a rainy night drive, in English"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
lyrics-mcp
An MCP server that writes original song lyrics with Claude. Built by the team behind MuseGen, an AI music platform.
Give it a brief, get back a title and a full set of lyrics marked up with English
section tags — [Verse], [Pre-Chorus], [Chorus], [Bridge], [Outro] — that stay
English whatever language the lyrics themselves are in. That is the format music
generation models expect, so the output pastes straight in.
Bring your own Anthropic API key. There is no hosted service behind this: the server runs on your machine, calls the Anthropic API with your credentials, and sends nothing anywhere else.
Quick start
There is nothing to install. Add this to your MCP client's config — for Claude Code,
.mcp.json in your project root:
{
"mcpServers": {
"lyrics": {
"command": "uvx",
"args": ["--from", "git+https://github.com/musegen/musegen-lyrics-generator-mcp.git", "lyrics-mcp"],
"env": {
"ANTHROPIC_API_KEY": "sk-ant-..."
}
}
}
}Restart your client and ask it to write you a song.
This needs uv, which builds the server in a throwaway
environment on first launch and handles Python for you. If you would rather not put
your key in the config file, drop the env block and export ANTHROPIC_API_KEY in
the environment your client launches from.
Related MCP server: suno-mcp
Other ways to run it
Installed on your PATH. Python 3.10 or newer:
pip install git+https://github.com/musegen/musegen-lyrics-generator-mcp.git{
"mcpServers": {
"lyrics": {
"command": "lyrics-mcp",
"env": { "ANTHROPIC_API_KEY": "sk-ant-..." }
}
}
}Note that command is resolved against the PATH your MCP client sees, which is not
always the shell you installed from — a virtualenv or a --user install often lands
somewhere the client cannot find. If the server fails to start, use the absolute path
to the lyrics-mcp executable, or go back to uvx.
From a clone, for hacking on it:
{
"mcpServers": {
"lyrics": {
"command": "python",
"args": ["-m", "lyrics_mcp.server"],
"cwd": "/path/to/musegen-lyrics-generator-mcp",
"env": { "PYTHONPATH": "src", "ANTHROPIC_API_KEY": "sk-ant-..." }
}
}
}The tool
write_lyrics — one required argument, four optional ones.
Argument | Required | Description |
| yes | What the song is about. Concrete imagery beats abstraction: "walking home alone through a quiet city after a late shift" gets a much better song than "a sad song". |
| no | Language for the lyrics ( |
| no |
|
| no |
|
| no |
|
Returns {"title": ..., "lyrics": ...}.
Configuration
Everything is an environment variable. Only the first one is required.
Variable | Default | Purpose |
| — | Your API key. The Anthropic SDK also accepts |
| Anthropic API | Point the SDK at a gateway or proxy. |
|
| Which model writes the lyrics. |
|
| Where a declined request is retried (see below). Set to empty to disable. |
|
| Requests per minute this process will make. |
On the rate limit
LYRICS_MCP_RPM is a token bucket over this process's API calls. It exists because an
agent that gets stuck in a loop on this tool can spend a lot of your money quickly, and
ten calls a minute is more than any human songwriting session needs.
It is not a security control. It lives in the process, so it caps your own runaway loops and nothing else — every user runs their own copy and spends their own money.
On refusals
Safety classifiers sometimes decline a request, which is a real possibility for lyrics
about grief, violence or addiction. By default the server enables server-side fallbacks,
so a declined request is re-run on LYRICS_MCP_FALLBACK_MODEL inside the same API call
and you usually never notice. If the whole chain declines, you get a clear error, and
softening the wording of the brief normally gets a result.
Gateways that have not adopted the fallback beta will reject it; the server notices, logs a line to stderr, and carries on without it.
On cost
Every call is billed to your key at your model's rates. A song is typically a few
thousand output tokens. Check Anthropic's pricing
for the current numbers, and set LYRICS_MCP_MODEL to a smaller model if you would
rather trade some quality for cost.
From MuseGen
lyrics-mcp is built by the team behind MuseGen, an AI music
platform that takes an idea all the way to a finished track — lyrics, vocals, instrumentals
and music videos, in the browser.
This server stays independent of it. It runs on your machine, calls the Anthropic API with your key, and never talks to MuseGen. The hosted tools below are there if you would rather not run anything, or if you want to hear the lyrics actually sung.
Tool | What it does |
This tool, in a browser. Pick genre, mood, language and structure, then copy the lyrics or turn them straight into a song. | |
Paste in lyrics this server wrote and get a produced track — vocals or instrumental, in a style you choose. | |
Free copy-and-paste style prompts by genre, for whichever generation model you use. | |
Upload the finished track and get an MV back. |
The rest of the kit lives at musegen.ai/tools — vocal remover, BPM detector, key finder, audio-to-MIDI and MP3-to-WAV, all free.
Development
smoke_test.py checks prompt assembly, output parsing, the rate limiter and the tool
schema. It needs no API key and makes no network calls:
pip install -e .
python smoke_test.pyLicense
MIT — see LICENSE.
Available Tools
1 toolwrite_lyricsA
Write a complete set of original song lyrics from a creative brief. Returns a title and a body marked up with English section tags ([Verse], [Pre-Chorus], [Chorus], [Bridge], [Outro]) that stay English whatever language the lyrics are in, ready to paste into a music-generation model.
Inputs: brief (required), mood, genre, language, +1 more. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is zero ambiguity between tools. The single tool's purpose is clearly defined and self-contained.
The sole tool name, write_lyrics, follows a clear verb_noun pattern. While there is no broader set to compare against, the name is descriptive and internally consistent.
A single tool feels thin for a domain like lyrics, but it is focused on one concrete action: generating complete lyrics. It is not an extreme mismatch, just minimal.
The tool covers the core workflow of generating original lyrics with structure tags, which fully addresses the server's apparent purpose. Minor gaps exist, such as no separate editing or variation tools, but these are workable around.
Maintenance
Related MCP Connectors
Write lyrics in 100+ styles, score them, generate full songs with 4 engines, split stems. OAuth.
Generate full songs with vocals, instrumentals and sound effects from text. One server for Suno, Google Lyria, Mureka, MiniMax, ACE-Step, YuE and ElevenLabs. Your agent can quote the credit cost before generating, start a song, wait for it to finish and return download links. Sign in with OAuth; optional daily credit caps; retries never charge twice.
Create songs from prompts or lyrics, check credits, and access your private library with OAuth.
AI songwriting studio: lyrics, Suno prompts, cover art, lyric and music videos, release planning.
Related MCP Servers
- AlicenseAqualityDmaintenanceEnables AI-powered music generation through natural language commands, supporting both inspiration mode (AI-generated lyrics and style) and custom mode (user-provided lyrics and parameters) to create songs with direct download links.43MIT
- FlicenseNot gradedqualityDmaintenanceEnables AI music generation and management through the Suno API, supporting text prompts, custom lyrics, track status monitoring, and credit management.16-
- AlicenseNot gradedqualityDmaintenanceEnables AI-powered music generation through natural language commands, supporting inspiration and custom modes with dual song outputs.1MIT
- AlicenseNot gradedqualityBmaintenanceEnables agents to edit short lyrics in authorized songs by uploading audio, selecting a phrase, supplying replacement words, previewing the result, and exporting the finished track through scoped tools.MIT