Image Generation Tools

Overview

The OpenGraph MCP Server includes a powerful suite of image generation tools that allow your AI assistant to create professional visuals on demand. Whether you need technical diagrams for documentation, social media cards, icons, or marketing illustrations, these tools handle it all.

• generateImage – Create new images from text prompts
• iterateImage – Refine and modify existing generated images
• exportImageAsset – Save images to your local filesystem
• inspectImageSession – Review generation history and find assets

generateImage

Create professional images from text prompts. Supports multiple image types including illustrations, diagrams (Mermaid, D2, Vega), icons, social cards, and QR codes.

Parameters

Example: Generate Social Card

Create a social card for my blog post titled "Getting Started with MCP" 
with a dark theme and the OpenGraph.io branding

Example: Generate Diagram

Generate an auth flow diagram showing:
1. User enters credentials
2. Server validates against database
3. JWT token returned
4. Client stores token

Use the github-dark style preset.

iterateImage

Refine, modify, or create variations of an existing generated image. Use this to make targeted edits without regenerating from scratch.

Parameters

Use Cases

• Change colors: "Change the primary color to #0033A0"
• Add elements: "Add a title at the top"
• Style changes: "Make it more minimalist"
• Fix issues: "Remove the text in the corner"
• Crop: Specify coordinates to crop to a specific region

exportImageAsset

Export a generated image to a specific file path on your local filesystem. Use this to save images directly to your project.

Parameters

inspectImageSession

Retrieve detailed information about an image generation session and all its assets. Useful for reviewing what was generated and finding asset IDs for iteration.

Parameters

Returns

• Session metadata (creation time, name, status)
• List of all assets with their prompts, toolchains, and status
• Parent-child relationships showing iteration history

Aspect Ratio Presets

Workflow Example

Here's a typical workflow for generating and exporting an image:

User: Create an OG image for my blog post about "Building REST APIs with Node.js"
       Use a dark tech theme with blue accents.

AI: I'll generate that image for you...
    [Calls generateImage with appropriate parameters]
    
    Generated! Here's the preview. Session ID: abc-123, Asset ID: def-456

User: Can you make the title bigger and add a subtle gradient?

AI: I'll update that for you...
    [Calls iterateImage with sessionId, assetId, and new prompt]
    
    Updated! Here's the new version.

User: Perfect! Save it to my project's public/images folder.

AI: I'll export that for you...
    [Calls exportImageAsset with destination path]
    
    Saved to /Users/you/project/public/images/blog-rest-apis-og.png

Best Practices

• Be specific in prompts – Include details about colors, style, and composition
• Use style presets – They provide consistent, professional results
• Iterate rather than regenerate – Small changes are faster with iterateImage
• Use appropriate aspect ratios – Each platform has optimal dimensions
• Provide project context – Helps the AI match your brand

Related