Skip to main content
Glama

GenPixy AI: Whiteboard Animation & Faceless Video Generator

Create an explainer video

create_video

Starts a narrated explainer video from a topic or script and returns the video object (status queued). Free videos have a watermark and are 60 seconds or less in 720p; balance videos use the account balance and have no watermark (get_options lists the costs). Send a unique idempotency_key per video so a retry never makes a second video.

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": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoOptional. plan: uses the weekly videos of the person's GenPixy subscription, no watermark. balance: uses the account balance, no watermark. free: watermark, 60 seconds or less in 720p, a daily limit; only in AI apps connected with GenPixy sign-in. Default: plan when the person has a subscription that covers this length; else free when GenPixy is connected in an AI app and the options allow it; else balance. When the subscription's videos are used up, the answer says when they come back and how to use the balance instead: ask the person before you spend their balance.
musicNo
styleNowhiteboard: hand-drawn whiteboard animation. animate: cartoon animation with characters. flat: Color Board (bold colored scenes).whiteboard
voiceNomale
promptYesA topic, notes, or a full script. Line breaks and Markdown lists are fine. Write it in the language the narration should use.
secondsNoTarget length.
languageNoauto: narration follows the prompt language (76 languages).auto
big_boardNoAll scenes on one board with a zoom-out recap at the end.
subtitlesNo
zoom_diveNoThe camera flies into an icon when the next scene looks closer at it.
resolutionNo720p
orientationNolandscape
idempotency_keyNoOptional. One unique string per video, for example a UUID. A retry with the same value returns the same video. The HTTP API also takes it as the Idempotency-Key header.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / mode / description
      Previous value: -"Optional. balance: uses the account balance, no watermark; the only mode with an API key. free: watermark, 60 seconds or less in 720p, a daily limit; only in AI apps connected with GenPixy sign-in. Default: free when GenPixy is connected in an AI app and the options allow it, else balance."New value: +"Optional. plan: uses the weekly videos of the person's GenPixy subscription, no watermark. balance: uses the account balance, no watermark. free: watermark, 60 seconds or less in 720p, a daily limit; only in AI apps connected with GenPixy sign-in. Default: plan when the person has a subscription that covers this length; else free when GenPixy is connected in an AI app and the options allow it; else balance. When the subscription's videos are used up, the answer says when they come back and how to use the balance instead: ask the person before you spend their balance."
    • changedInput schema / properties / mode / enum
      Previous value: -[
      -  "free",
      -  "balance"
      -]New value: +[
      +  "free",
      +  "balance",
      +  "plan"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / idempotency_key / description
      Previous value: -"Optional. One unique string per video, for example a UUID."New value: +"Optional. One unique string per video, for example a UUID. A retry with the same value returns the same video. The HTTP API also takes it as the Idempotency-Key header."
    • changedInput schema / properties / mode / description
      Previous value: -"Optional. free: watermark, 60 seconds or less in 720p, a daily limit; only when GenPixy is connected in an AI app. balance: uses the account balance, no watermark. Default: free when the options allow it and GenPixy is connected in an AI app, else balance."New value: +"Optional. balance: uses the account balance, no watermark; the only mode with an API key. free: watermark, 60 seconds or less in 720p, a daily limit; only in AI apps connected with GenPixy sign-in. Default: free when GenPixy is connected in an AI app and the options allow it, else balance."
  3. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare a non-read-only, non-destructive, non-idempotent write; the description goes beyond them by disclosing that the call returns immediately with status 'queued' (async job) and that some modes consume paid account balance. That billing consequence is the highest-risk behavior here and is called out. It does not describe failure modes or how long rendering typically takes.

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?

Three sentences, front-loaded with what the tool does and returns, then the mode constraints, then the idempotency rule. Every sentence carries information. Minor overlap with the mode parameter's schema description is the only redundancy.

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 13-parameter creation tool with no output schema, the description covers the essentials: async return shape, cost implications, free-tier limits, and retry safety. It does not address polling for completion (presumably get_video's job) or rate limits, but nothing critical for invoking it correctly is missing.

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 62%, so the schema already explains mode, prompt, style, language, seconds, big_board and idempotency_key in detail. The description reinforces the two riskiest parameters (mode economics and the idempotency key) but largely restates what the schema says, and adds nothing for the undocumented flags (music, voice, subtitles, resolution, orientation). Baseline 3 is appropriate.

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 opens with a specific verb and resource ('Starts a narrated explainer video from a topic or script') and states the return value ('returns the video object (status queued)'), which immediately separates it from the read-only siblings get_video, list_videos, get_account and get_options. get_options is named explicitly as the place to look up costs, so the creation-vs-inspection boundary is unambiguous.

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 real operating conditions: free mode carries a watermark and a 60s/720p cap, balance mode spends account balance, and a unique idempotency_key is required per video so retries are safe. It points to get_options for cost lookup. It stops short of an explicit 'do not call this to re-generate/duplicate an existing video' exclusion, so a 4 rather than 5.

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