Skip to main content
Glama

generateImage

Generate images from text descriptions. Provide a prompt, choose size and quality, and set an absolute output path to create custom image assets for game and web development projects.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
outputPathAbsoluteYesThe absolute path where the image should be written out.
promptYesText description of the desired image content
qualityNoThe quality of the image.
sizeNoSize of the generated image

Implementation Reference

  • src/index.ts:25-69 (registration)
    The tool 'generateImage' is registered via server.tool() on the McpServer instance. This is the registration point that binds the name, schema, and handler together.
    server.tool(
      'generateImage',
      {
        outputPathAbsolute: z.string().describe('The absolute path where the image should be written out.'),
        prompt: z.string().describe("Text description of the desired image content"),
        quality: z.enum(["auto", "low", "medium", "high"]).optional().describe("The quality of the image."),
        size: z.enum(['1024x1024', '1024x1536', '1536x1024', 'auto']).optional().describe("Size of the generated image"),
      },
      async ({ prompt, size = "1024x1024", quality="low", outputPathAbsolute}) => {
        try {
          const response = await openai.images.generate({
            model: "gpt-image-1",
            prompt,
            n: 1,
            size: size,
            quality: quality,
          });
    
          if (!response.data) {
            throw new Error(`API did not return any data.`);
          }
    
          if (!response.data[0]?.b64_json) {
            throw new Error('API did not return image data');
          }
          
          const imageData = response.data[0].b64_json;
          const bytes = Buffer.from(imageData, 'base64');
    
          writeFileSync(outputPathAbsolute, bytes)
    
          return {
            content: [
                {
                    type: 'text',
                    text: `The image is now available at ${outputPathAbsolute}.`
                }
            ],
            message: "Image generated successfully!"
          };
        } catch (error) {
          throw new Error(`Error generating image: ${JSON.stringify(error, null, 2)}`, {cause: error});
        }
      }
    );
  • Zod schema definitions for the 'generateImage' tool inputs: outputPathAbsolute (string), prompt (string), quality (enum: auto/low/medium/high, optional), size (enum: 1024x1024/1024x1536/1536x1024/auto, optional).
    {
      outputPathAbsolute: z.string().describe('The absolute path where the image should be written out.'),
      prompt: z.string().describe("Text description of the desired image content"),
      quality: z.enum(["auto", "low", "medium", "high"]).optional().describe("The quality of the image."),
      size: z.enum(['1024x1024', '1024x1536', '1536x1024', 'auto']).optional().describe("Size of the generated image"),
    },
  • The async handler function that executes the tool logic. It calls OpenAI's images.generate API with the gpt-image-1 model, receives base64 image data, writes it to the specified output path, and returns a success message.
    async ({ prompt, size = "1024x1024", quality="low", outputPathAbsolute}) => {
      try {
        const response = await openai.images.generate({
          model: "gpt-image-1",
          prompt,
          n: 1,
          size: size,
          quality: quality,
        });
    
        if (!response.data) {
          throw new Error(`API did not return any data.`);
        }
    
        if (!response.data[0]?.b64_json) {
          throw new Error('API did not return image data');
        }
        
        const imageData = response.data[0].b64_json;
        const bytes = Buffer.from(imageData, 'base64');
    
        writeFileSync(outputPathAbsolute, bytes)
    
        return {
          content: [
              {
                  type: 'text',
                  text: `The image is now available at ${outputPathAbsolute}.`
              }
          ],
          message: "Image generated successfully!"
        };
      } catch (error) {
        throw new Error(`Error generating image: ${JSON.stringify(error, null, 2)}`, {cause: error});
      }
    }
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

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/jbrower95/mcp-asset-gen'

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