This MCP server generates high-quality images from text prompts using AI, automatically enhancing prompts and configuring settings for optimal output without requiring prompt engineering skills.
From the registry: AI image generation and editing with prompt optimization and quality presets. Powered by Nano Banana
Please install the `mcp-image` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Gemini API key** — Get an API key from Google AI Studio (https://aistudio.google.com/apikey)
- **Node.js 22+** — Requires Node.js 22 or higher
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","mcp-image"]
- required environment variables:
- `GEMINI_API_KEY`: Gemini API key (example: `<your-api-key>`)
- optional environment variables:
- `IMAGE_OUTPUT_DIR`: Absolute path for generated images (default ./output) (example: `/Users/you/images`)
- `IMAGE_QUALITY`: Quality preset: fast (default), balanced, quality (example: `balanced`)
- `SKIP_PROMPT_ENHANCEMENT`: Set to true to disable automatic prompt optimization (example: `false`)
Note: AI image generation using Nano Banana 2 / Pro (Gemini). Automatic prompt optimization via Gemini 2.5 Flash.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GEMINI_API_KEYrequiredAPI key for accessing the Gemini image generation service.IMAGE_OUTPUT_DIRrequiredAbsolute path to the directory where generated images will be saved.