nanobanana-pro-mcp
An MCP server that provides AI-powered image generation, format conversion, and smart asset placement for Claude Code.
README
Nano Banana Pro Image Generation for Claude Code
An MCP (Model Context Protocol) server that provides AI-powered image generation, format conversion, and smart asset placement for Claude Code.
Features
generate_image- Generate images from text prompts with automatic aspect ratio detectionconvert_image- Convert images between formats (PNG, JPG, WebP, ICO, ICNS)save_asset- Smart asset placement with project-aware naming conventions
Smart Detection
-
Aspect Ratio: Automatically detects the best size based on prompt keywords
- "icon", "avatar", "logo" → 1:1 (1024x1024)
- "banner", "hero", "header" → 16:9 (1280x720)
- "mobile", "story", "splash" → 9:16 (720x1280)
- "photo", "traditional" → 4:3 (1216x896)
-
Project Type: Detects your project framework and places assets accordingly
- Next.js, React, Vue →
public/images/orsrc/assets/ - Unity →
Assets/Images/ - Godot →
assets/images/ - Python →
assets/orstatic/images/
- Next.js, React, Vue →
-
Naming Convention: Matches your project's existing style
- kebab-case, snake_case, PascalCase, camelCase
Installation
From PyPI (Recommended)
# Using uv (recommended)
uv pip install nanobanana-pro-mcp
# Or using pip
pip install nanobanana-pro-mcp
Prerequisites
- Python 3.10+
- uv (recommended) or pip
Configure Claude Code
Add to your Claude Code MCP settings (~/.claude.json or project's .mcp.json):
{
"mcpServers": {
"nanobanana": {
"command": "uvx",
"args": [
"nanobanana-pro-mcp",
"--api-key=YOUR_API_KEY",
"--base-url=http://127.0.0.1:8045/v1"
]
}
}
}
Configuration Options
| Argument | Required | Description |
|---|---|---|
--api-key |
Yes | Your API key for the image generation service |
--base-url |
Yes | Base URL of the OpenAI-compatible image API |
--model |
No | Model name (default: gemini-3-pro-image) |
Usage Examples
Generate an Image
"Generate a futuristic city skyline at sunset"
The MCP will:
- Detect this should be a wide/banner image (16:9)
- Generate the image via your configured API
- Return a temporary file path and suggested filename
Convert Format
"Convert /tmp/futuristic-city.png to WebP"
For icons:
"Convert /tmp/app-logo.png to ICO"
This creates a proper Windows icon with all required sizes (16x16 through 256x256).
Save to Project
"Save /tmp/futuristic-city.png to my Next.js project at /home/user/my-app"
The MCP will:
- Detect it's a Next.js project
- Find or create
public/images/ - Apply kebab-case naming (or match existing convention)
- Save as
futuristic-city.png
Supported Formats
| Format | Read | Write | Notes |
|---|---|---|---|
| PNG | ✅ | ✅ | Default output format |
| JPG/JPEG | ✅ | ✅ | Converts RGBA to RGB |
| WebP | ✅ | ✅ | Great for web projects |
| ICO | ✅ | ✅ | Multi-size Windows icons |
| ICNS | ✅ | ✅ | macOS icons (basic support) |
Development
Local Setup
git clone https://github.com/rzgrozt/nanobanana-pro-mcp.git
cd nanobanana-pro-mcp
# Create virtual environment
uv venv
source .venv/bin/activate
# Install in development mode
uv pip install -e .
Testing Locally
nanobanana-pro-mcp --api-key=test --base-url=http://localhost:8045/v1
License
MIT License - see LICENSE for details.
Contributing
Contributions are welcome! Please open an issue or submit a pull request.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.