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.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。