Skip to main content
Glama

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

Video from reference images, videos and audio

pixverse_create_video_fusion

Generate a video from reference images (and, on models that take them, reference videos and audio) cited in the prompt as @image1, @video1, @audio1 (PixVerse's Reference mode), with V5 (default), V5.6, C1 or third-party models (Seedance, Kling 4.0 / O3, MiniMax H3, Wan 3.0, Gemini Omni Flash); each model takes its own number of references. Naming a model makes duration and quality required. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/create-fusion.

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_video_fusion"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoSeed for a repeatable result (native PixVerse models only).
waitNoWait up to ~50 s for the job to finish (default true); false returns the id at once.
audioNotrue adds generated sound where the model has an audio toggle (see the model capabilities page).
emailNoThe PixVerse account email (pixverse_list_accounts). Optional: by default a random account with a free slot.
modelNoDefault v5 (with duration 5 and quality 540p).
promptYesWhat happens, citing @image1..@imageN, @video1.., @audio1.. in order.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
qualityNoRequired when model is given.
durationNoSeconds; required when model is given.
relax_modeNoThird-party models only (400 on PixVerse's own). Left out (or true), the plan's discount for the model applies; false pays the full price.
audio_pathsNoReference audio (@audio1 first), on the models that take them, up to 10.
image_pathsNoReference images in order (@image1 first): paths from pixverse_upload_file. Up to 30 by model (v5 3, v5.6 and pixverse-c1 7).
video_pathsNoReference videos (@video1 first), on the models that take them, up to 10.
aspect_ratioNoDefault 16:9.
preview_modeNotrue makes a fast lower-quality preview at 20% off credits (native PixVerse models only, paid plans).
off_peak_modeNotrue runs it in Off-Peak mode at a lower credit cost (native PixVerse models; the discount depends on the plan). Such a job is not waited for: read it later with pixverse_get_video.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations (which already flag this as a non-read-only, open-world, non-idempotent write), the description discloses cost implications ('Uses PixVerse credits'), timing ('Waits up to ~50 s'), and the follow-up path ('returns the video_id for pixverse_get_video'). The one notable gap is that the non-waiting behavior for off-peak jobs appears only in the parameter description, not the top-level text.

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?

The opening sentence is dense but front-loads the purpose, the citation syntax, and the model families; the following short sentences each deliver a distinct fact (required params, credits, waiting, handoff, endpoint). The long model enumeration is the only part that pushes against readability.

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 a 16-parameter generative tool with no output schema, the description covers the essentials an agent needs: reference syntax, model-dependent constraints, credit cost, blocking-vs-async behavior, and where the resulting video_id goes next. It could be stronger by stating account selection and the preview/off-peak non-waiting interaction at the top level.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already carries the per-parameter meaning and the baseline is 3. The description adds one genuinely useful cross-parameter link — that @image1..@imageN in the prompt correspond to ordered entries — but most of its model/duration/quality notes duplicate what the schema already says.

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?

The description states a specific verb and resource ('Generate a video from reference images') and immediately pins down the distinguishing mode: PixVerse's Reference mode with @image1/@video1/@audio1 citations in the prompt. That is enough for an agent to tell it apart from a plain text-to-video sibling without opening a schema.

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

Usage Guidelines3/5

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

It gives conditional rules ('naming a model makes duration and quality required', references only apply on models that take them, off-peak jobs are not waited for) but never says when to choose this tool over a sibling or when not to use it. Usage is implied by the mode description rather than stated as routing guidance.

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