Gemini Image Studio
About
MCP server for AI image generation and editing with Google Gemini (NanoBanana). Features structured JSON editing — decompose any image into a blueprint, then edit specific components with dot-notation paths. 5 tools, 10 built-in presets for ads, web, and social media.
Details
- Author
- udhaykumarbala
- Downloads
- 373
- Categories
- Media, AI
Jump to
- generate_image — Create images from text or JSON prompts with preset support
- decompose_image — Analyze images into structured JSON blueprints
- edit_image — Edit via JSON dot-notation paths or natural language
- get_presets — 10 built-in presets for common formats (Facebook ads, Instagram stories, hero images, OG images, YouTube thumbnails, etc.)
- list_generated — Browse generated images with metadata and edit history
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Gemini Image StudioCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
—
generate_image
Create a new image from text prompt, JSON prompt, or both. Supports presets for common asset types (ads, web, social).
decompose_image
Analyze an image and return a structured JSON blueprint of all visual components. Use this as the first step before editing an image with JSON changes.
edit_image
Edit an existing image using structured JSON changes (dot-notation paths) or natural language instructions. For JSON edits, run decompose_image first to get the blueprint.
get_presets
List available asset presets with dimensions, tips, and conventions for ads, web pages, and social media.
list_generated
Browse and search previously generated images in the output directory, with optional metadata and blueprints.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"gemini image studio": {
"gemini-image-studio-mcp": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}
}McpServers
{
"gemini-image-studio-mcp": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}Features
- generate_image — Create images from text or JSON prompts with preset support - decompose_image — Analyze images into structured JSON blueprints - edit_image — Edit via JSON dot-notation paths or natural language - get_presets — 10 built-in presets (Facebook ads, Instagram stories, hero images, OG images, YouTube thumbnails, etc.) - list_generated — Browse generated images with metadata and edit history ## What Makes This Different Structured JSON editing pipeline: generate → decompose → edit specific fields (e.g., subject[0].hair.color) → regenerate. Precise changes without affecting the rest of the image.Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
