Vidu MCP Stdio
System Components
The system consists of two main components:
- UVX MCP Server
- Python-based cloud server
- Communicates directly with the Vidu API
- Provides full video generation capabilities
Installation & Configuration
Prerequisites
- Python 3.10 or higher
- UV/UVX
- Vidu API Key: Obtain from Vidu Platform (This feature requires API Credits, which must be purchased separately on Vidu Platform)
Get Dependencies
- Python:
- Download and install from the official Python website
- Ensure Python is added to your system path
- UV/UVX:
- Install uv and set up our Python project and environment:
Mac/Linux
curl -LsSf https://astral.sh/uv/install.sh | sh
Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"
How to Use MCP Server
-
Get Vidu API Key
- Visit the Vidu Platform
- Register or log into your account
- Create and copy your API key from the account settings
-
Download Required Dependencies
- Python: Install Python 3.10 or above
- UV/UVX: Install the latest stable version of UV & UVX
-
Configure MCP Client
- Open your MCP client (e.g., Claude for Desktop or Cursor)
- Locate the client settings
- Open mcp_config.json (or relevant config file)
- Add the configuration based on the method you use:
{"mcpServers": {"Vidu": {"command": "uvx","args": ["vidu-mcp"],"env": {"VIDU_API_KEY": "api-key-here","VIDU_API_HOST": "api-host-here"}}}}
- Save the config file
-
Restart MCP Client or Refresh MCP Server
- Fully close and reopen your MCP client
- Or use the "Refresh MCP Server" option if supported
Client-specific Configuration
Claude for Desktop
- Open the Claude application
- Navigate to Claude > Settings > Developer > Edit Config
- Open the claude_desktop_config.json file
- Windows
- Mac : /Library/Application\ Support/Claude/claude_desktop_config.json
- Add the configuration above and save
- Restart Claude
- If connected successfully: the homepage will not show any error and the MCP status will be green
- If connection fails: an error message will be shown on the homepage
Cursor
- Open the Cursor application
- Go to Settings > Model Context Protocol
- Add a new server
- Fill in the server details as in the JSON config above
- Save and restart or refresh the MCP server
Usage Examples
Text-to-Video
Use natural language prompts via Claude or Cursor to generate videos.
Basic Example:
In an ultra-realistic fashion photography style featuring light blue and pale amber tones, an astronaut in a spacesuit walks through the fog. The background consists of enchanting white and golden lights, creating a minimalist still life and an impressive panoramic scene.
Advanced Example with Parameters:
Generate a night cityscape video with the following parameters:Prompt: Skyscraper lights twinkling under the night sky, with car lights forming streaks on the roadModel: viduq1Style: generalDuration: 5 secondsAspect Ratio: 16:9Resolution: 1080pMovement Amplitude: middle