Skip to main content
Glama

MiniMax MCP Server by useapi.net (third-party)

Create a song

minimax_create_music

Generate 1-3 songs with MiniMax Music (music-3.0, music-2.6) from a style prompt, your own lyrics, or a reference track (a cover); for spoken text use minimax_create_speech. Supply prompt, lyrics, referenceMusicId or a combination. One song generation per MiniMax account at a time (429 while one runs, including songs started on minimax.io); uses the account's MiniMax Audio credits, not its Hailuo video credits (412 without them). Waits up to ~50 s and returns each track's musicId, status and, once completed, audio_url; else call minimax_get_music. POST /music/create.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "minimax_create_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
modelNoDefault music-3.0.
titleNoSong name, max 40 characters.
lyricsNoYour own lyrics, max 3500 characters; structure tags on their own line ([Verse], [Chorus], [Bridge], [Outro]...). Left out, the model writes lyrics from prompt (MiniMax may refuse with 422: add lyrics, set instrumental, or rephrase). More lyrics make a longer song: there is no duration input. Not with instrumental.
promptNoStyle and subject in one: genre, mood, tempo, instruments, vocal type, and what the song is about. Max 2000 characters.
accountNoThe MiniMax account id (minimax_list_accounts). Omit to let the API pick the account with the fewest music generations running; with referenceMusicId the reference's account is used.
quantityNoTracks from this one call, 1-3 (default 1); each is its own song with its own musicId and finishes on its own.
replyRefNoOptional reference of yours, stored and returned with the result and webhook. Up to 1,024 characters.
replyUrlNoOptional webhook: the API POSTs the finished result (same shape as the get tool's record) to this URL. Up to 1,024 characters.
instrumentalNotrue: no vocals (leaving lyrics empty is not enough). Cannot be combined with lyrics or referenceMusicId. Default false.
referenceMusicIdNoThe musicId of a track the new song should follow, making it a cover: a reference from minimax_upload_music_reference or any song on the same account. The cover runs on that account. For the closest result pass the reference's own lyrics and no prompt, e.g. user:12345-minimax:123456789012345678-music:987654321098765 (it names the account).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.6/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-read-only, non-idempotent, open-world write, and the description goes well beyond them: one concurrent generation per account with a 429, consumption of MiniMax Audio credits and a 412 without them, and a ~50 s wait with partial results. The only mild gap is that webhook payload/retry behavior is left to the schema field rather than described.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the core action and inputs, then the operational constraints (concurrency, credits, wait, endpoint). It is a dense single paragraph with a lot of parenthetical detail, but nearly every clause carries actionable information rather than restating the name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 11-parameter, zero-required generation tool with no output schema, the description supplies the missing return contract (musicId, status, audio_url once completed) and names the fallback getter. Combined with the credit and concurrency constraints, an agent has everything needed to call it correctly and interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds real meaning on top: the valid combination of prompt/lyrics/referenceMusicId, that omitting account lets the API pick the least-loaded account while a reference pins the cover to its own account, and that each quantity track is an independent song. That is genuine semantic value beyond the field-level text.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Generate 1-3 songs with MiniMax Music") plus the supported models and the three input modes (style prompt, own lyrics, reference track cover). It explicitly names the sibling it is not for ("for spoken text use minimax_create_speech"), so an agent can route without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives explicit routing rules: use minimax_create_speech for spoken text, use minimax_get_music when the wait times out or wait=false is set. It also states which inputs may be combined and which cannot (instrumental cannot pair with lyrics or referenceMusicId), covering the when and when-not cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources