A
licenseA
qualityD
maintenanceEnables text-to-image generation, image editing, and multi-image composition using Google's Gemini 2.5 Flash Image API. Supports flexible aspect ratios and character consistency across generations.
1
MIT
Nano Banana
by saroby
Integrates with Google's AI services to provide image generation capabilities through Gemini and Imagen models, featuring support for custom aspect ratios and negative prompts.
Enables image generation using Google Gemini and Imagen models, allowing users to specify prompts, aspect ratios, and quality modes (Flash or Pro) while managing generated output.
Click on "Deploy 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., "@Nano Banana generate a cinematic 16:9 landscape of a futuristic city using the pro model"
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.
@saroby/nanobanana-mcp
Google Gemini image generation MCP server (Nano Banana).
Features
generate_image - Generate images using Google Gemini models
flashmode: gemini-2.5-flash-image (fast, ~2-3s)promode: gemini-3-pro-image-preview (high quality, ~5-8s)
list_images - List generated images in a directory
Related MCP server: Nano Banana MCP Server
Setup
Get API Key
Go to Google AI Studio
Create an API key
Install in Claude Code
claude mcp add nanobanana -e GEMINI_API_KEY=your-key-here -- npx -y @saroby/nanobanana-mcpManual Usage
GEMINI_API_KEY=your-key-here npx @saroby/nanobanana-mcpTools
generate_image
Parameter | Type | Required | Description |
| string | Yes | Image description (1-8192 chars) |
|
| No | Model selection (default: flash) |
| enum | No |
|
| string | No | Elements to exclude |
| string | No | Save directory (default: ./nanobanana-images) |
| number | No | Number of images 1-4 (default: 1) |
list_images
Parameter | Type | Required | Description |
| string | No | Directory to search (default: ./nanobanana-images) |
Development
npm install
npm run build
npm run dev # watch modeLicense
MIT
Available Tools
2 toolsgenerate_imageB
Generate images using Google Gemini models. Supports 'flash' (fast, gemini-2.0-flash-exp) and 'pro' (high quality, imagen-3.0) models.
Inputs: prompt (required), model, aspect_ratio, negative_prompt, +2 more.
list_imagesB
List generated images in the specified directory.
Inputs: directory.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
B3.3/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have completely distinct purposes: generate_image creates new images, while list_images retrieves existing ones. There is no overlap in functionality, making it impossible for an agent to confuse them.
Naming Consistency5/5
Both tools follow a consistent verb_noun pattern (generate_image, list_images) with clear, descriptive names. The naming convention is uniform and predictable throughout the set.
Tool Count2/5
With only two tools, the server feels severely under-scoped for an image generation domain. There are obvious gaps like deleting, updating, or managing images beyond listing, making it difficult for agents to perform complete workflows.
Completeness2/5
The tool surface is highly incomplete for image generation and management. While it covers creation and listing, it lacks essential operations such as deleting images, updating metadata, or viewing detailed image properties, which will cause agent failures in many scenarios.
Maintenance
ActivityInactive
ResponsivenessOutdated data
Related MCP Connectors
LLM chat, text tools, image generation, editing, batch image jobs, and asynchronous video generation
Create images and videos from prompts, with options for image mixing, reference images, and start/…
AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.
Generate images, videos and music with model discovery, cost estimates and asynchronous results.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables generating, editing, and manipulating images using Google Gemini Flash 2.5 through natural language prompts. Supports text-to-image generation, image editing, multi-image composition, and batch processing with direct file management.174 npm4MIT
- FlicenseNot gradedqualityCmaintenanceEnables image generation and editing using Google's Gemini models with support for model selection and custom aspect ratios. Users can generate high-quality images or modify existing ones through natural language prompts while controlling specific parameters like quality and dimensions.-
- AlicenseNot gradedqualityDmaintenanceEnables image generation, editing, and refinement using Google's Gemini 2.5 Flash Image model with support for multi-image composition and style transfer.ISC