Volcengine Image Generation MCP Server
A Model Context Protocol (MCP) server that provides tools for generating images using Volcengine's text-to-image API.
Features
- Text-to-image generation using Volcengine's doubao-seedream-3-0-t2i-250415 model
- Support for multiple image sizes and formats
- Configurable parameters including seed, guidance scale, and watermark
- Proper error handling and validation
- TypeScript implementation with full type safety
Installation
- Clone or download this repository
- Install dependencies:
npm install
- Build the project:
npm run build
Configuration
Set the required environment variable:
export VOLCENGINE_API_KEY="your_api_key_here"
Usage
Running the server
npm start
Development mode
npm run dev
Available Tools
generate_image
Generate images from text prompts using Volcengine's API.
Parameters:
prompt(required): Text description of the image to generatemodel(optional): Model ID (default: doubao-seedream-3-0-t2i-250415)size(optional): Image size (default: 1024x1024)seed(optional): Random seed for reproducible resultsguidance_scale(optional): How closely to follow the prompt (1-10)watermark(optional): Whether to add watermark (default: true)response_format(optional): Return format - 'url' or 'b64_json' (default: url)
Supported sizes:
- 1024x1024 (1:1)
- 864x1152 (3:4)
- 1152x864 (4:3)
- 1280x720 (16:9)
- 720x1280 (9:16)
- 832x1248 (2:3)
- 1248x832 (3:2)
- 1512x648 (21:9)
Example Usage
{
"name": "generate_image",
"arguments": {
"prompt": "A beautiful sunset over mountains",
"size": "1024x1024",
"guidance_scale": 7.5
}
}
MCP Client Configuration
Add this server to your MCP client configuration:
{
"mcpServers": {
"volcengine-image": {
"command": "node",
"args": ["path/to/build/index.js"],
"env": {
"VOLCENGINE_API_KEY": "your-api-key"
}
}
}
}
Error Handling
The server provides comprehensive error handling for:
- Invalid API keys
- Rate limiting
- Invalid parameters
- Network errors
- API response errors
License
MIT