MCP Image Gen
Generates images from text prompts using Google's Gemini AI models with customizable aspect ratios and resolutions up to 4K, automatically saving images locally.
README
MCP Image Gen
A Model Context Protocol (MCP) server for generating images using Google's Gemini AI models.
Features
- 🎨 Generate high-quality images from text prompts using Gemini AI
- 📐 Customizable aspect ratios (1:1, 16:9, 9:16, 4:3, 3:4)
- 🔧 Configurable image sizes (small to 4K resolution)
- ⚙️ Flexible configuration via JSON file
- 💾 Automatic local image saving with organized filenames (saves to ~/gemini_images by default)
- 🚀 Built on the MCP SDK for seamless integration
⚠️ Known Issues
- Aspect ratio and image size parameters may not be working correctly - Images are currently being generated in landscape format regardless of the specified aspect ratio. This is being investigated. The API calls appear correct, but the Gemini API may not be respecting the configuration parameters as expected.
Models Supported
- gemini-3-pro-image-preview (Default): Professional-grade, supports up to 4K resolution
- gemini-2.5-flash-image: Optimized for speed, generates 1024px resolution
Installation
- Clone the repository:
git clone https://github.com/Legorobotdude/mcp-image-gen.git
cd mcp-image-gen
- Install dependencies:
pnpm install
- Build the project:
pnpm build
Configuration
Environment Variables
Set your Gemini API key:
export GEMINI_API_KEY=your_api_key_here
Get your API key from Google AI Studio.
Config File (Optional)
Create a config.json file in the project root to customize defaults:
{
"model": "gemini-3-pro-image-preview",
"defaultAspectRatio": "1:1",
"defaultImageSize": "large",
"outputDirectory": "~/gemini_images"
}
Available Options:
model:"gemini-3-pro-image-preview"or"gemini-2.5-flash-image"defaultAspectRatio:"1:1","16:9","9:16","4:3", or"3:4"defaultImageSize:"small"(1K - 1024px)"medium"(2K - 2048px)"large"(2K - 2048px)"xlarge"(4K - 4096px - only for gemini-3-pro-image-preview)
outputDirectory: Path where generated images will be saved (default:~/gemini_images, can use absolute paths or~for home directory)
Usage with Claude Desktop
Add to your Claude Desktop configuration file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"mcp-image-gen": {
"command": "node",
"args": ["/absolute/path/to/mcp-image-gen/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}
Tool: generate_image
Generate an image from a text prompt.
Parameters
- prompt (required): Text description of the image to generate
- aspectRatio (optional): Aspect ratio -
"1:1","2:3","3:2","3:4","4:3","4:5","5:4","9:16","16:9","21:9" - imageSize (optional): Resolution -
"small"(1K),"medium"(2K),"large"(2K),"xlarge"(4K) - negativePrompt (optional): Describe what you DON'T want in the image
Example Usage in Claude
Generate an image of a serene mountain landscape at sunset with vibrant colors
Create a 16:9 image of a futuristic city skyline at night in xlarge size
Generate a portrait of a wise old wizard with a long beard, aspect ratio 3:4, medium size
Response Format
The tool returns a JSON response with:
{
"success": true,
"imagePath": "/Users/yourusername/gemini_images/1234567890_serene_mountain_landscape.png",
"prompt": "serene mountain landscape at sunset",
"model": "gemini-3-pro-image-preview",
"aspectRatio": "1:1",
"imageSize": "large",
"message": "Image generated successfully and saved to: /Users/yourusername/gemini_images/1234567890_serene_mountain_landscape.png"
}
Image Quality Notes
- All generated images include a SynthID watermark (Google's digital watermark)
- gemini-3-pro-image-preview: Best for high-quality, detailed images up to 4K
- gemini-2.5-flash-image: Best for quick generation, fixed at 1024px resolution
Development
Watch mode for development:
pnpm dev
Build for production:
pnpm build
Troubleshooting
"GEMINI_API_KEY environment variable is required"
Make sure you've set the GEMINI_API_KEY environment variable or added it to your MCP configuration.
Images not generating
- Check your API key is valid
- Verify you have internet connectivity
- Ensure the output directory is writable
Size options not working
The gemini-2.5-flash-image model only supports 1024px resolution regardless of the size parameter. Use gemini-3-pro-image-preview for higher resolutions.
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。