Gemini Image Studio
@udhaykumarbala
About Gemini Image Studio
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.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"gemini-image-studio-mcp": {
"command": "npx",
"args": [
"-y",
"gemini-image-studio-mcp"
],
"env": {
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>"
}
}
}
}Tools
5Create a new image from text prompt, JSON prompt, or both. Supports presets for common asset types (ads, web, social).
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 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.
List available asset presets with dimensions, tips, and conventions for ads, web pages, and social media.
Browse and search previously generated images in the output directory, with optional metadata and blueprints.
Overview
What is Gemini Image Studio?
Gemini Image Studio is an MCP server that integrates with Google's Gemini to generate, edit, and decompose images using text or JSON prompts. It offers preset support and a structured JSON editing pipeline for precise, targeted changes. It is designed for developers and content creators who need programmatic control over image generation and modification.
How to use Gemini Image Studio?
—
Key features of Gemini Image Studio
- 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
Use cases of Gemini Image Studio
- Generate social media assets (ads, stories, thumbnails) using presets
- Decompose an existing image into a modifiable JSON blueprint
- Edit specific image fields (e.g.,
subject[0].hair.color) without affecting the rest of the image - Browse previously generated images and their edit history for reuse or iteration
FAQ from Gemini Image Studio
What makes Gemini Image Studio different from other image generation tools?
It uses a structured JSON editing pipeline: generate → decompose → edit specific fields → regenerate. This allows precise changes without affecting the rest of the image.
What presets are available?
The server includes 10 built-in presets for common formats such as Facebook ads, Instagram stories, hero images, OG images, and YouTube thumbnails.
Can I edit images using natural language?
Yes, the edit_image tool supports both JSON dot-notation paths and natural language instructions for editing.
Frequently asked questions
What makes Gemini Image Studio different from other image generation tools?
It uses a structured JSON editing pipeline: generate → decompose → edit specific fields → regenerate. This allows precise changes without affecting the rest of the image.
What presets are available?
The server includes 10 built-in presets for common formats such as Facebook ads, Instagram stories, hero images, OG images, and YouTube thumbnails.
Can I edit images using natural language?
Yes, the `edit_image` tool supports both JSON dot-notation paths and natural language instructions for editing.
Basic information
More Media & Design MCP servers
百度地图 MCP Server
baidu-mapsBaidu Map MCP Server
Riddle Quiz Maker
Riddle.comCreates and manages quizzes, polls, surveys, personality tests, forms, predictors, minigames and leaderboards on Riddle.com – with branching logic, custom design, live stats and embed code.
Lamina — On-brand product photos, video & try-ons
LaminaGenerate on brand product videos from Claude Code (or any assistant) in one line. Lamina turns a brief + your brand kit into finished product photos, video reels, and campaign banners - no prompt engineering; brand guard
uxgen
uxgenA library of conversion components for e-commerce, built on A/B tested mechanics and handed straight to your coding agent. 65 pieces drawn from mechanics that have been A/B tested in real stores: cart drawer with the ups
SVGator
SVGatorDrive your SVGator account from any AI assistant. Prompt an animation, get an editable project back, and export it as SVG, Lottie, GIF, MP4, and more, then open it in the editor to finish by hand.
Comments