Vidu API
Dashboard
Docs
Sign in

Vidu MCP Streamable Http

Installation & Configuration

Prerequisites

Vidu API Key: Obtain from Vidu Platform (This feature requires API Credits, which must be purchased separately on Vidu Platform)

How to Use MCP Server

1. Get Vidu API Key

  • Visit the Vidu Platform
  • Register or log into your account
  • Create and copy your API key from the account settings

2. Configure MCP Client

Launch Inspector Tool

  1. Launch Inspector
    npx @modelcontextprotocol/inspector
  2. Configure Connection Parameters
    • Select Transport Type as Streamable HTTP
    • Configure in the Authorization section:
      • Header Name: x-md-Authorization
      • Bearer Token: Token {your_api_key} (Replace {your_api_key} with your actual API key)
  3. Establish Connection
    • Click the Connect button to establish

Configure for Cursor / Claude for Desktop

  • 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":{
"url": "https://api.vidu.com/mcp/v1",
"headers": {
"Authorization": "Token {your_api_key}"
}
}
}
}
  • Save the config file

3. 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

  1. Open the Claude application
  2. Navigate to Claude > Settings > Developer > Edit Config
  3. Open the claude_desktop_config.json file
    • Windows
    • Mac : ~/Library/Application\ Support/Claude/claude_desktop_config.json
  4. Add the configuration above and save
  5. 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

  1. Open the Cursor application
  2. Go to Settings > Model Context Protocol
  3. Add a new server
  4. Fill in the server details as in the JSON config above
  5. 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 road
Model: viduq1
Style: general
Duration: 5 seconds
Aspect Ratio: 16:9
Resolution: 1080p
Movement Amplitude: middle

Reference Video Generation

Basic Example:
Image 1: https://image1.png
Image 2: https://image2.png
Image 3: https://image3.png
Generate a video where the black cat from Image 2 and Pikachu from Image 3 are playing and fighting on the seaside path from Image 1. Pikachu hits the black cat on the head, and the black cat pounces on Pikachu. The actions are fast, the scene is intense, and the image quality is realistic.
Advanced Example with Parameters:
Generate a video with the following parameters:
Prompt: The black cat from Image 2 and Pikachu from Image 3 are playing and fighting on the seaside path from Image 1. Pikachu hits the black cat on the head, and the black cat pounces on Pikachu. The actions are fast, the scene is intense, and the image quality is realistic.
Image 1: https://image1.png
Image 2: https://image2.png
Image 3: https://image3.png
Model: viduq1 (Reference)
Style: general
Duration: 5 seconds
Aspect Ratio: 16:9
Resolution: 1080p