Skip to main content
Glama

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

Generate music

pixverse_create_music

Generate a song or an instrumental from a prompt with music-2.6 (MiniMax Music 2.6), music-v1 (ElevenLabs Music), lyria-3-pro-preview (Google Lyria 3 Pro); default music-2.6. Your own lyrics on music-2.6 and music-v1 (else the model writes them), instrumental: true for no vocals, and up to 10 reference images on lyria-3-pro-preview. Uses PixVerse credits per track (see the pricing page). Waits up to ~50 s, then returns the audio_id for pixverse_get_music. POST /music/create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "pixverse_create_music"
  }
}

Input Schema

NameRequiredDescriptionDefault
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
emailNoThe PixVerse account email (pixverse_list_accounts). Optional: by default a random account with a free slot.
modelNoDefault music-2.6.
lyricsNoThe words to sing (music-2.6 and music-v1 only); not with instrumental.
promptYesThe track you want; up to 2000 characters on music-2.6, 4000 characters on music-v1, 5000 characters on lyria-3-pro-preview.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
image_pathsNolyria-3-pro-preview only: reference images that condition the music, paths from pixverse_upload_file.
instrumentalNotrue makes a track without vocals; not with lyrics.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that PixVerse credits are consumed per track with a pricing pointer, that the call blocks for ~50 s, and that it returns an audio_id for pixverse_get_music. Those are exactly the cost and blocking traits an agent needs before invoking an openWorldHint, non-idempotent generation.

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?

Very dense and front-loaded — models first, then constraints, then cost and return behavior. Every clause carries information, though the second sentence strings several unrelated constraints together, requiring careful parsing.

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

Completeness4/5

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

For an 8-parameter generation tool with no output schema, it covers model selection, cost, blocking behavior, and the returned handle. Minor gaps remain around failure handling and what to do if wait=false and the job does not complete, but the essential calling information is present.

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?

With 100% schema coverage the baseline is 3, and the description adds genuine cross-parameter semantics: lyrics are restricted to two models and mutually exclusive with instrumental, image_paths applies only to lyria-3-pro-preview, and per-model prompt length limits. Some of this duplicates the schema text, keeping it from a 5.

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 a song or an instrumental from a prompt") and enumerates the three models with the default, plus the underlying endpoint POST /music/create. It also distinguishes the artifact type from sibling video tools by naming the follow-up retrieval tool pixverse_get_music.

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

Usage Guidelines4/5

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

Gives clear conditional guidance for the key choices: your own lyrics on music-2.6 and music-v1 versus the model writing them, `instrumental: true` for no vocals, and reference images only on lyria-3-pro-preview. It does not explicitly contrast this tool with pixverse_create_music_video or explain when to prefer a music video over plain audio.

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