Nanobanana MCP
Provides generative AI capabilities including image generation, editing, restoration, icon creation, pattern creation, diagram generation, and story generation via Google's Gemini API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Nanobanana MCPgenerate a banana icon"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
🍌 Nanobanana MCP
A powerful Model Context Protocol (MCP) server for generative AI media tasks.
Overview
Nanobanana MCP brings generative capabilities directly to your MCP clients (like Claude Desktop or other AI agents). It leverages Google's Gemini API to generate images, icons, patterns, diagrams, and even visual stories.
This server implements the Model Context Protocol, allowing seamless integration with any MCP-compliant tool.
Related MCP server: MCP MediaCrea
✨ Features
Generate Images: Create images from text prompts (
nanobanana_generate_image).Edit Images: Modify existing images using text instructions (
nanobanana_edit_image).Restore Images: Denoise and restore image quality (
nanobanana_restore_image).Generate Icons: Create app icons and favicons in various sizes (
nanobanana_generate_icon).Generate Patterns: Create seamless textures and tileable patterns (
nanobanana_generate_pattern).Generate Diagrams: Create flowcharts, UML, and technical diagrams (
nanobanana_generate_diagram).Story Generation: Generate sequential visual stories (
nanobanana_generate_story).
🚀 Getting Started
Prerequisites
Bun (v1.2+ recommended)
A Google Gemini API Key
Installation
Clone the repository:
git clone <repository-url> cd nanobanana-mcpInstall dependencies:
bun installCreate a
.envfile in the root directory:cp .env.example .env # if example exists, otherwise create new
Configuration
Set the following environment variables in your .env file:
Variable | Description | Default |
| Your Google Gemini API Key (Required for generation) |
|
| The Gemini model to use |
|
| Directory to save generated assets |
|
| Logging verbosity (info, debug, warn, error) |
|
Note: The server will fallback to a Mock Generator if no API key is provided, returning placeholder images for testing.
🏃♂️ Usage
Running the Server
Start the MCP server directly:
bun run index.tsIntegration with Claude Desktop
Add the following to your claude_desktop_config.json:
{
"mcpServers": {
"nanobanana": {
"command": "bun",
"args": ["run", "/absolute/path/to/nanobanana-mcp/index.ts"],
"env": {
"GEMINI_API_KEY": "your_api_key_here"
}
}
}
}🛠️ Development
Run the test suite to verify functionality:
# Run unit tests
bun test
# Run specific phase tests
bun test src/phase2.test.ts📜 License
This project is licensed under the MIT License.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/kamil-perczynski/nanobanana-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server