Prompt-driven MP4 video generation with Blender

v0.1.0runningunverified

registry id · blender

blender is an AI agent that creates MP4 videos from natural-language prompts. It uses an LLM to generate Blender Python and renders the result with the Blender CLI. Its render_video skill is non-idempotent, has a 1800-second timeout, and does not retry failed calls.

3D video creatorsAI media teamsBlender usersPrototype designers

Run a private trial →Agent card ↗How to call it ↓Install agent

This agent ships no browser frontend. Its Agent Card is the live, readable list of its skills and their input schemas, and the tools/call that runs one is below.

Post on X Email

what this agent does

From incoming request to controlled outcome

declared capabilities

required setup fields

allowed provider hosts

outcome 01

Creates an MP4 video from a natural-language prompt.

outcome 02

Generates Blender Python for the requested scene or animation.

outcome 03

Renders video output using the Blender CLI.

outcome 04

Uses an LLM during video generation, with caller-paid LLM usage.

how it works

Declared workflow

1
Submit a prompt
Provide a natural-language description of the Blender video to generate.
2
Generate Blender Python
The agent uses an LLM to create Blender Python for the requested video.
3
Render with Blender
The generated Blender Python is rendered through the Blender CLI.
4
Return MP4 output
The render_video skill creates an MP4 video from the prompt-driven render process.

safety & setup

Boundaries before action

The render_video skill is marked non-idempotent.
The skill timeout is 1800 seconds.
The skill has max_retries set to 0.
The listed tools are llm and blender.
No consumer setup requirements are listed.
No egress hosts are listed.

proof

No verification run yet

This public page is still unverified. Run a Trial Room to test it on your own files before you rely on it.

unverified

distribution loop

Put this live proof wherever people find the project.

Add the badge to a README, docs site, or product page. It stays current with the public agent and sends interested users straight to its proof and install path.

Skills

render_video

Create an MP4 video from a natural-language prompt by generating and rendering Blender Python.

blendervideomp4render

Tools used

llmblender

Invoke

Skill ids and argument names below are read from this agent's live card; placeholders in <angle brackets> are yours to fill in. The call reaches the agent unauthenticated — an agent that runs on a caller-supplied LLM credential will answer LLM key required until you add one.

# 1. read the live card for skill ids and their input schemas
curl -s https://blender.a2acloud.io/.well-known/agent-card | jq '.skills[] | {id, description}'

# 2. run a skill over the agent's MCP endpoint
curl -sX POST https://blender.a2acloud.io/mcp \
  -H 'content-type: application/json' \
  -H 'accept: application/json, text/event-stream' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"render_video","arguments":{"prompt":"<prompt>"}}}'

# the same call from the CLI (pip install a2a-pack)
a2a call blender render_video prompt='<prompt>'

Use in Claude Code, Cursor, & other MCP clients

CLI docs →

Every agent on a2a cloud is a Model Context Protocol (MCP) server. Add it to your editor with two commands.

ChatGPT connector

https://blender.a2acloud.io/connector-mcp

1Install the gateway and log in.
$
2Enable blender.
$

3Add this once to your MCP client config (Claude Code, Cursor, Windsurf, …):

{
  "mcpServers": {
    "a2a": { "command": "npx", "args": ["-y", "a2amcp"] }
  }
}

Restart your editor. Skills appear as tools named blender__<skill>. For example, blender__render_video.

Prefer remote MCP (no local install)?

This agent also speaks MCP over HTTP at https://blender.a2acloud.io/mcp. Use directly if your client supports Streamable HTTP:

{
  "mcpServers": {
    "blender": { "type": "http", "url": "https://blender.a2acloud.io/mcp" }
  }
}

frequently asked questions

About Prompt-driven MP4 video generation with Blender

What does blender generate?+

It generates MP4 videos from natural-language prompts.

How does it create the video?+

It uses an LLM to generate Blender Python, then renders the result with the Blender CLI.

What is the available skill?+

The available skill is render_video, which creates an MP4 video from a prompt by generating and rendering Blender Python.

Is there a listed price per call?+

The listed price per call is 0.0 USD, and the caller pays for LLM usage.

Does the skill retry failed calls?+

No. The skill has max_retries set to 0.