Skip to main content
Glama
sanxfxteam

Gemini MCP Image Generation Server

by sanxfxteam

generateImage

Create custom images using text prompts, customizable aspect ratios, and output formats via the Gemini MCP Image Generation Server to suit your visual content needs.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
aspectRatioNo
outputFormatNo
promptYes

Implementation Reference

  • server.js:23-91 (registration)
    Full registration of the 'generateImage' MCP tool using server.tool(), including input schema, handler function, and tool metadata with parameter descriptions.
    server.tool(
      "generateImage",
      {
        prompt: z.string(),
        aspectRatio: z.string().optional(),
        outputFormat: z.string().optional()
      },
      async (params) => {
        // Default values
        const prompt = params.prompt || "Default image prompt";
        const aspectRatio = params.aspectRatio || "1:1";
        const outputFormat = params.outputFormat || "png";
    
        try {
          // Initialize the Imagen 3 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);
    
          // Extract the generated image data (base64 encoded)
          for (const part of result.response.candidates[0].content.parts) {
            // Based on the part type, either show the text or save the image
            if (part.text) {
              console.log(part.text);
              return {
                content: [{
                    type: "text",
                    text: part.text
                }]
              }
            } else if (part.inlineData) {
              const imageData = part.inlineData.data;
              const buffer = Buffer.from(imageData, 'base64');
              fs.writeFileSync('gemini-native-image.png', buffer);
              console.log('Image saved as gemini-native-image.png');
              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 }
        }
      }
    );
  • server.js:30-82 (handler)
    The handler function for 'generateImage' tool. Uses GoogleGenerativeAI (Gemini model) to generate image from prompt, handles text or image parts in response, saves image to file, and returns MCP-formatted content (text or image).
    async (params) => {
      // Default values
      const prompt = params.prompt || "Default image prompt";
      const aspectRatio = params.aspectRatio || "1:1";
      const outputFormat = params.outputFormat || "png";
    
      try {
        // Initialize the Imagen 3 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);
    
        // Extract the generated image data (base64 encoded)
        for (const part of result.response.candidates[0].content.parts) {
          // Based on the part type, either show the text or save the image
          if (part.text) {
            console.log(part.text);
            return {
              content: [{
                  type: "text",
                  text: part.text
              }]
            }
          } else if (part.inlineData) {
            const imageData = part.inlineData.data;
            const buffer = Buffer.from(imageData, 'base64');
            fs.writeFileSync('gemini-native-image.png', buffer);
            console.log('Image saved as gemini-native-image.png');
            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}`
          }]
        };
      }
    },
  • Zod schema for input validation of 'generateImage' tool parameters.
    {
      prompt: z.string(),
      aspectRatio: z.string().optional(),
      outputFormat: z.string().optional()
    },
  • Tool metadata including description and JSON schema-like parameter definitions for 'generateImage'.
    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 }
    }
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Tool has no description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness1/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Related Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sanxfxteam/gemini-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server