MCP Catalogs
Home

Veo-4-API

by Anil-matcha·147·Score 48

Python wrapper for Veo 4 API with MCP server for AI-generated 4K videos with integrated audio and character consistency.

mediaai-llmdeveloper-tools
35
Forks
1
Open issues
1 mo ago
Last commit
2d ago
Indexed

Overview

Veo-4-API is a comprehensive Python wrapper for Google DeepMind's Veo 4 AI video generation API, accessible via MuAI. It enables developers to create native 4K videos up to 30 seconds with integrated audio, character consistency, and advanced camera controls. The project includes a dedicated MCP server implementation that allows AI assistants like Claude Desktop to directly invoke video generation tools through the Model Context Protocol.

Try asking AI

After installing, here are 6 things you can ask your AI assistant:

you:Content creators generating AI videos for social media with consistent characters
you:Developers integrating video generation capabilities into their applications
you:AI assistants creating custom video content in response to user requests
you:What is the Veo 4 API?
you:How do I get API access to Veo 4?
you:What video formats and resolutions are supported?

When to choose this

Choose this MCP server when you need to generate high-quality AI videos with character consistency and integrated audio directly within AI assistants like Claude Desktop or Cursor.

When NOT to choose this

Avoid if you need open-source self-hosted solutions, as this relies on MuAPI's proprietary API with potential vendor lock-in.

Tools this server exposes

9 tools extracted from the README
  • text_to_video

    Generate native 4K video from text prompt.

  • image_to_video

    Animate static images into 4K video.

  • text_to_video_with_audio

    Generate video with integrated audio from text prompt.

  • image_to_video_with_audio

    Animate images with synchronized audio.

  • character_video

    Generate videos with consistent character identity.

  • extend_video

    Extend an existing video segment.

  • video_edit

    Edit existing videos with natural language prompts.

  • upload_file

    Upload local images or videos to the platform.

  • wait_for_completion

    Wait for video generation to complete.

Comparable tools

runway-mcppika-mcpstability-mcphuggingface-video-gen

Installation

Installation

Via Pip (Recommended)

pip install veo-4-api

Configuration

Create a .env file in the root directory and add your [MuAPI](https://muapi.ai) API key:

MUAPI_API_KEY=your_muapi_api_key_here

Running the MCP Server

  1. Ensure MUAPI_API_KEY is set in your environment.
  2. Run the server:

``bash python3 mcp_server.py ``

  1. To test with the MCP Inspector:

``bash npx -y @modelcontextprotocol/inspector python3 mcp_server.py ``

Claude Desktop Configuration

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "veo-4": {
      "command": "python3",
      "args": ["/path/to/Veo-4-API/mcp_server.py"]
    }
  }
}

FAQ

What is the Veo 4 API?
Veo 4 is Google DeepMind's state-of-the-art AI video generation model featuring native 4K output, up to 30-second clips, integrated audio, character consistency, and advanced camera controls.
How do I get API access to Veo 4?
Access to Veo 4 is provided through MuAI (https://muapi.ai). You'll need to obtain an API key from their platform to use this wrapper.
What video formats and resolutions are supported?
Veo 4 generates native 4K video (not upscaled) in 16:9, 9:16 (TikTok/Reels), and 1:1 aspect ratios with quality tiers of 1080p and 4K.

Compare Veo-4-API with

GitHub →

Last updated · Auto-generated from public README + GitHub signals.