Skip to main content
Glama

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

Generate a video

pixverse_create_video

Generate a video from text, an image (first_frame_path) or an effect template (template_id from pixverse_list_effects) with PixVerse V6 (default), C1, V5.x or third-party models (Seedance 2.5 / 2.0, Kling 4.0 / O3 / 3.0, Veo 3.1, MiniMax H3, Wan 3.0, Grok Imagine, HappyHorse, FLUX 3, Gemini Omni Flash). Durations, qualities and ratios depend on the model (see the model capabilities page); third-party models need a Pro plan or higher. Uses PixVerse credits. Waits up to ~50 s, then returns the video_id for pixverse_get_video. POST /videos/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": "pixverse_create_video"
  }
}

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 v6. A template_id makes the template's own model run.
promptNoWhat happens in the video. Required unless first_frame_path, template_images or template_id is given.
maxJobsNoOverride the account's maxJobs (jobs at once) for this request, 1-8.
qualityNoOptional on the native v6 / v5.x models (default 720p on v6, 540p on v5.x); required on pixverse-c1 and third-party models.
durationNoSeconds. Optional on v6, v5.6, v5.5, v5 and v5-fast (default 5); required on pixverse-c1 and third-party models. 1-30 by model.
auto_soundNov5 only: true adds sound, false removes a template's default sound.
multi_shotNov6 only: several camera angles and cuts instead of one continuous shot.
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.
template_idNoAn effect template from pixverse_list_effects; it sets the model, duration and allowed qualities.
aspect_ratioNoText to video only (an image sets it); default 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.
last_frame_pathNoThe last frame, with a template_id only (pixverse_create_video_frames for first-to-last without a template): a path from pixverse_upload_file.
template_imagesNoFor multi-input templates: up to 5 image paths (the template's effect_type sets how many); not with first_frame_path.
first_frame_pathNoThe first frame (image to video): a path from pixverse_upload_file.
lip_sync_tts_promptNov5 only: lines the character speaks.
sound_effect_promptNov5 only: the sound to add, e.g. waves hitting the shore.
lip_sync_tts_speaker_idNov5 only: a speaker_id from pixverse_list_lipsync_voices.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Beyond the annotations, the description discloses cost behavior (consumes PixVerse credits, preview_mode at 20% off, off_peak_mode discount depends on plan, relax_mode pricing), timing behavior (waits ~50 s then returns video_id; off_peak jobs are not waited for), and an access gate (Pro plan for third-party models). These are exactly the operational facts an agent needs before committing a paid, non-idempotent job.

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

Conciseness3/5

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

The core purpose and return value are front-loaded, which is good, but the definition is a single sprawling sentence and the parenthetical enumeration of roughly fourteen third-party model names largely duplicates the model enum already present in the schema. That enumeration costs readability without adding selection value.

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 22-parameter generation tool with no output schema, the description covers the essentials: what gets produced, the returned video_id, the ~50 s wait ceiling, and credit/plan constraints. It does not explain what happens on failure or what the response contains when wait=false, but the critical call-shaping 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?

Schema description coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: template_id overrides model, duration and allowed qualities, and aspect_ratio applies only to text-to-video. It also states v6 is the default model. The remaining parameter guidance (per-model duration/quality limits) is deferred to an external capabilities page rather than spelled out.

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 names a specific verb and resource (generate a video) and enumerates the three input modes it accepts: text, an image via first_frame_path, or an effect template via template_id. It also routes to siblings by name (pixverse_list_effects for templates, pixverse_get_video for retrieval), so an agent can distinguish it from the other create_* tools without opening the schema.

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?

It gives clear preconditions and alternatives in places: third-party models require a Pro plan, template_id comes from pixverse_list_effects, first-to-last without a template should use pixverse_create_video_frames, and results are read with pixverse_get_video. It does not explicitly contrast itself with pixverse_create_final_video, pixverse_extend_video, or pixverse_modify_video, so the routing is helpful but not exhaustive.

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