Content
[](https://mseep.ai/app/el-el-san-vidu-mcp-server)
# Tool List
[](https://smithery.ai/server/@el-el-san/vidu-mcp-server)
This is a Model Context Protocol (MCP) server for integrating with the Vidu video generation API. It provides a tool to generate videos from images using Vidu's powerful AI models.
## Features
- **Image to Video Conversion**: Generate videos from static images with customizable settings
- Support for multiple models: viduq1, vidu1.5, vidu2.0
- Model-specific time and resolution constraints
- BGM support for 4-second videos
- Callback URL support for asynchronous notifications
- **Generation Status Check**: Monitor video generation task progress with credit usage information
- **Image Upload**: Easily upload images for use with the Vidu API (up to 10MB)
## Prerequisites
- Node.js (v14 or higher)
- Vidu API key (obtainable from the [Vidu website](https://vidu.com))
- TypeScript (for development)
## Installation
### Installation via Smithery
Automatically install the Vidu Video Generation Server for Claude Desktop using [Smithery](https://smithery.ai/server/@el-el-san/vidu-mcp-server):
```bash
npx -y @smithery/cli install @el-el-san/vidu-mcp-server --client claude
```
### Gemini CLI Configuration
To use with Gemini CLI, add server settings to `~/.gemini/settings.json`:
```json
{
"mcpServers": {
"vidu": {
"command": "node",
"args": [
"your_path/vidu-mcp-server/build/index.js"
],
"env": {
"VIDU_API_KEY": "your_api_key_here"
}
}
}
}
```
**Note**: Replace `your_path` with the actual installation directory path and `your_api_key_here` with your Vidu API key.
### Manual Installation
1. Clone this repository:
```bash
git clone https://github.com/el-el-san/vidu-mcp-server.git
cd vidu-mcp-server
```
2. Install dependencies:
```bash
npm install
```
3. Create a `.env` file based on `.env.template` and add your Vidu API key:
```
VIDU_API_KEY=your_api_key_here
```
## Usage
### For Gemini CLI
1. Build TypeScript code:
```bash
npm run build
```
2. Configure Gemini CLI (see Gemini CLI Configuration section above)
3. Restart Gemini CLI to load MCP
## Tools
### 1. Image to Video Conversion
Convert static images to videos with customizable parameters.
Parameters:
- `image_url` (required): URL of the image to convert to video
- `prompt` (optional): Text prompt for video generation (up to 1500 characters)
- `duration` (optional): Output video duration (seconds) (model-specific)
- **viduq1**: 5 seconds only
- **vidu1.5/vidu2.0**: 4 or 8 seconds (default 4 seconds)
- `model` (optional): Model name for generation ("viduq1", "vidu1.5", "vidu2.0", default "vidu2.0")
- `resolution` (optional): Output video resolution (model/time-specific)
- **viduq1 (5s)**: 1080p only
- **vidu1.5/vidu2.0 (4s)**: "360p", "720p", "1080p" (default "360p")
- **vidu1.5/vidu2.0 (8s)**: "720p" only
- `movement_amplitude` (optional): Amplitude of object movement within frames ("auto", "small", "medium", "large", default "auto")
- `seed` (optional): Random seed for reproducibility
- `bgm` (optional): Add BGM to video (boolean, default false, 4-second videos only)
- `callback_url` (optional): URL for asynchronous notification on generation status change
Example request:
```json
{
"image_url": "https://example.com/image.jpg",
"prompt": "A quiet lake with mountains in the background",
"duration": 8,
"model": "vidu2.0",
"resolution": "720p",
"movement_amplitude": "medium",
"seed": 12345,
"bgm": false
}
```
### 2. Generation Status Check
Check the status of running video generation tasks.
Parameters:
- `task_id` (required): Task ID returned by the image to video conversion tool
Example request:
```json
{
"task_id": "12345abcde"
}
```
### 3. Image Upload
Upload images for use with the Vidu API.
Parameters:
- `image_path` (required): Local path to the image file
- `image_type` (required): Image file type ("png", "webp", "jpeg", "jpg")
Example request:
```json
{
"image_path": "/path/to/your/image.jpg",
"image_type": "jpg"
}
```
## Troubleshooting
- **API Key Issues**: Ensure your Vidu API key is correctly set in the `.env` file (for manual setup) or Gemini CLI configuration (for Gemini CLI setup)
- **File Upload Errors**: Verify that the image file is valid and within size limits (upload-image tool: 10MB, direct URL images: up to 50MB)
- **Connection Issues**: Ensure you have internet access and can reach the Vidu API server
- **Gemini CLI Issues**:
- Ensure the server is built (`npm run build`) before configuring with Gemini CLI
- Verify that the path in settings.json points to the correct `build/index.js` file
- Restart Gemini CLI after making configuration changes
- Set `"disabled": false` in server settings
