generateImage
Create images from text prompts using Google Gemini's AI, with options for aspect ratio and output format control.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | ||
| aspectRatio | No | ||
| outputFormat | No |
Implementation Reference
- server.js:25-61 (handler)The core handler function that generates images using the Google Generative AI Gemini model. It processes the prompt, calls the image generation model, extracts the inline image data, and returns it in the expected MCP format. Handles errors by returning a text error message.async (params) => { const prompt = params.prompt || "rendered image of fly pig"; const outputFormat = params.outputFormat || "png"; try { // Initialize gemini-2.0-flash-exp-image-generation model const model = genAI.getGenerativeModel({ model: "gemini-2.0-flash-exp-image-generation", generationConfig: { responseModalities: ['Text', 'Image'], }, }); // Generate the image const result = await model.generateContent(prompt); for (const part of result.response.candidates[0].content.parts) { if (part.inlineData) { const imageData = part.inlineData.data; return { content: [{ type: "image", data: imageData, mimeType: `image/${outputFormat}` }] }; } } } catch (error) { console.error("Image generation error:", error); return { content: [{ type: "text", text: `Error generating image: ${error.message}` }] }; } },
- server.js:20-24 (schema)Zod schema defining the input parameters for the generateImage tool: required 'prompt' string, optional 'aspectRatio' and 'outputFormat' strings.{ prompt: z.string(), aspectRatio: z.string().optional(), outputFormat: z.string().optional() },
- server.js:18-70 (registration)The MCP server.tool() call that registers the 'generateImage' tool, specifying name, input schema, handler function, and tool metadata including parameter descriptions.server.tool( "generateImage", { prompt: z.string(), aspectRatio: z.string().optional(), outputFormat: z.string().optional() }, async (params) => { const prompt = params.prompt || "rendered image of fly pig"; const outputFormat = params.outputFormat || "png"; try { // Initialize gemini-2.0-flash-exp-image-generation model const model = genAI.getGenerativeModel({ model: "gemini-2.0-flash-exp-image-generation", generationConfig: { responseModalities: ['Text', 'Image'], }, }); // Generate the image const result = await model.generateContent(prompt); for (const part of result.response.candidates[0].content.parts) { if (part.inlineData) { const imageData = part.inlineData.data; return { content: [{ type: "image", data: imageData, mimeType: `image/${outputFormat}` }] }; } } } catch (error) { console.error("Image generation error:", error); return { content: [{ type: "text", text: `Error generating image: ${error.message}` }] }; } }, { description: "Generate an image using Gemini API", parameters: { prompt: { type: "string", description: "The text description of the image to generate" }, aspectRatio: { type: "string", description: "Aspect ratio of the image (e.g., '1:1', '16:9')", optional: true }, outputFormat: { type: "string", description: "Output image format ('png' or 'jpeg')", optional: true } } } );