Skip to main content
MCP (Model Context Protocol) is a model context protocol launched by Anthropic that allows AI models (such as Claude, GPT, etc.) to call external tools through standardized interfaces. With the Veo MCP Server provided by AceData Cloud, you can directly use Google Veo to generate AI videos in AI clients like Claude Desktop, VS Code, Cursor, etc.

​
Feature Overview

The Veo MCP Server provides the following core functionalities:
  • Text to Video Generation — Generate high-quality videos from text prompts
  • Image to Video Generation — Generate videos based on images
  • Multi-Model Support — Supports models like veo3, veo2, veo31-fast-ingredient, etc.
  • Multiple Resolutions — Supports output formats like 4K, 1080p, GIF, etc.
  • Various Aspect Ratios — Supports ratios like 16:9, 9:16, etc.
  • 1080p Upgrade — Upgrade generated videos to 1080p
  • Task Querying — Monitor generation progress and obtain results

​
Prerequisites

Before using, you need to obtain an AceData Cloud API Token:
  1. Register or log in to the AceData Cloud platform
  2. Go to the Veo Videos API page
  3. Click “Acquire” to get the API Token (first-time applicants receive free credits)

​
Installation Configuration

pip install mcp-veo

​
Method 2: Source Installation

git clone https://github.com/AceDataCloud/MCPVeo.git
cd MCPVeo
pip install -e .
Once installed, you can use the mcp-veo command to start the service.

​
Using in Claude Desktop

Edit the Claude Desktop configuration file:
  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the following configuration: 
{
  "mcpServers": {
    "veo": {
      "command": "mcp-veo",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}
If using uvx (no need to install the package in advance): 
{
  "mcpServers": {
    "veo": {
      "command": "uvx",
      "args": ["mcp-veo"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}
After saving the configuration, restart Claude Desktop to use Veo-related tools in the conversation.

​
Using in VS Code / Cursor

Create a .vscode/mcp.json in the project root directory: 
{
  "servers": {
    "veo": {
      "command": "mcp-veo",
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}
Or use uvx: 
{
  "servers": {
    "veo": {
      "command": "uvx",
      "args": ["mcp-veo"],
      "env": {
        "ACEDATACLOUD_API_TOKEN": "your API Token"
      }
    }
  }
}

​
Available Tools List

Tool NameDescription
veo_text_to_videoGenerate video from text prompts
veo_image_to_videoGenerate video based on images
veo_get_1080pUpgrade video to 1080p
veo_get_taskQuery status of a single task
veo_get_tasks_batchBatch query task statuses

​
Usage Examples

After configuration, you can directly call these functions in the AI client using natural language, for example:
  • “Help me generate a time-lapse video of the starry sky using Veo”
  • “Generate a 4K video from this landscape photo”
  • “Create a vertical 9:16 short video”
  • “Upgrade this video to 1080p”

​
More Information