Vidu

Provides access to Vidu video generation via MCP clients with API keys and host configuration.

python

5

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "shengshu-ai-vidu-mcp": {
      "command": "uvx",
      "args": [
        "vidu-mcp"
      ],
      "env": {
        "VIDU_API_KEY": "api-key-here",
        "VIDU_API_HOST": "api-host-here"
      }
    }
  }
}

You can access Vidu’s latest video generation models through applications that support the Model Context Protocol (MCP). This MCP server runs locally and connects to the Vidu API, enabling text-to-video, image-to-video, and related generation workflows from compatible clients like Claude or Cursor.

How to use

Use natural prompts in your MCP client to generate videos. You can start with text prompts to create content from scratch, or combine text with image prompts for more control. The MCP server handles requests to the Vidu API and returns video assets or viewable links.

To configure your MCP client, add the Vidu MCP server as a new MCP endpoint. You will provide the API key and host so the client can authenticate and send requests to Vidu.

When you send a request, you can leverage the following generation options: text-to-video, image-to-video, reference-to-video, and start-end-to-video, enabling a variety of creative workflows.

Example prompts can describe an ultra-realistic scene, a cityscape at night, or a cinematic moment with specific styles and durations. Start with a clear prompt, then refine with model type, style, duration, aspect ratio, and resolution as supported by your MCP client.

To ensure smooth operation, you must supply your Vidu API key and host to the MCP client configuration. These values are used by the server to authenticate with the Vidu service.

{
  "mcpServers": {
    "Vidu": {
      "command": "uvx",
      "args": [
        "vidu-mcp"
      ],
      "env": {
        "VIDU_API_KEY": "api-key-here", 
        "VIDU_API_HOST": "api-host-here"
      }
    }
  }
}

Available tools

Text-to-Video

Generate a video from a natural language prompt using the Vidu MCP integration.

Image-to-Video

Generate a video from a prompt with an accompanying image input to guide visuals.

Reference-to-Video

Generate a video guided by a reference image or scene described in text.

StartEnd-to-Video

Generate a video using start and end prompts to control framing or sequence.