Advertise
MCP.so
Sign In

Gemini Nanobanana MCP Server

@Junhan2

Repository

Basic information

Category

AI & Agents

License

MIT

Transports

stdio

Author

Junhan2

Submitted by

gangjoon

About Gemini Nanobanana MCP Server

MCP server for Google Gemini 2.5 Flash Image preview (text-to-image, editing, composition)

#gemini#nanobanana#claude#chatgpt

Gemini Nanobanana MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "gemini-nanobanana-mcp": {
      "command": "npx",
      "args": [
        "gemini-nanobanana-mcp@latest"
      ],
      "env": {
        "GEMINI_API_KEY": "your-api-key",
        "AUTO_SAVE": "true",
        "DEFAULT_SAVE_DIR": "~/Pictures/AI-Images",
        "LOG_LEVEL": "debug"
      }
    }
  }
}

Gemini Nanobanana MCP Server tools

4

Generate an image from a text prompt using Gemini 2.5 Flash Image

Edit an image using a prompt. Provide one input image via base64 or file path.

Compose a new image using multiple input images and a guiding prompt.

Transfer style from a style image to a base image, guided by an optional prompt.

Overview

What is Gemini Nanobanana Mcp?

Gemini Nanobanana Mcp is a beginner-friendly Model Context Protocol (MCP) server that brings Google’s Gemini 2.5 Flash image generation directly into Claude conversations. It enables text-to-image generation, image editing, multi-image composition, and style transfer—all through natural language prompts.

How to use Gemini Nanobanana Mcp?

Configure the server in Claude Desktop, Claude Code, or Cursor by adding a JSON entry with the npx command and your GEMINI_API_KEY environment variable. After restarting your client, simply ask Claude to generate, edit, or compose images. Images are auto-saved to ~/Downloads/gemini-images/ by default, and you can specify a custom path in your prompt.

Key features of Gemini Nanobanana Mcp

  • Text-to-image generation from any description
  • Edit uploaded images with natural language instructions
  • Combine multiple images into a collage or composition
  • Apply artistic style from one image to another
  • Auto‑save images to disk or disable with AUTO_SAVE=false
  • Optional HTTP mode for external integrations

Use cases of Gemini Nanobanana Mcp

  • Generate custom illustrations, logos, or concept art during a chat
  • Edit photos by describing the desired change (e.g., “make this black and white”)
  • Create collages by uploading multiple reference images
  • Apply a style reference image to a content image for artistic transfer
  • Automatically save every generated image to a local folder for later use

Frequently asked questions

1

What API key is required and where do I get it?

You need a Google AI Studio API key. Get one free at [Google AI Studio](https://aistudio.google.com/apikey) by signing in with your Google account.

2

How do I install Gemini Nanobanana Mcp in Claude Desktop on Mac?

Open Terminal and run the one‑line command provided in the README that writes the configuration JSON to `~/Library/Application Support/Claude/claude_desktop_config.json`, replacing `YOUR_API_KEY` with your actual key.

3

Why am I getting “GEMINI_API_KEY not set” error?

The API key is missing or incorrectly set. Double‑check your config file or environment variable, ensure there are no extra spaces, and restart your Claude client.

4

Can I change where images are saved or disable automatic saving?

Yes. Set `DEFAULT_SAVE_DIR` to a custom path, or set `AUTO_SAVE` to `false` to only save images when you explicitly request a path.

5

What image formats are supported and how do I get instant preview?

Supported formats: PNG, JPEG, WebP, and GIF. For instant preview in Claude Code, install the provided hooks from the repository—generated images will open automatically in Quick Look.

Comments

More AI & Agents MCP servers

TruVerifAI Panel-review

TruVerifAI

TruVerifAI's Panel Review is the guardian agent for AI's highest-stakes coding decisions: four frontier models argue over an AI coding agent's riskiest designs, diffs, and commits before they execute, with local review g

1

localscreenshot - website screenshot mcp for ai agents

localscreenshot is a Website screenshot MCP server and API available at https://localscreenshot.com/api. Localscreenshot screenshot api turns any public web page into an image or a PDF. Take the capture from one of 227 c

hausverbot

eliduarte37

BERGHAIN MCP server — sovereign AI stress-testing mcp / ai / multi-agent / adversarial / stress-test / claude

strac-mcp-dlp

strac-io

Detect and redact PII, PHI, PCI and secrets — SSNs, credit cards, passports, API keys and cloud credentials — in text and in local files, using the Strac DLP API. Five tools: redact_text, detect_sensitive_data, detect_fi

3

imageat

incendies

Official MCP server for imageat — AI image and video generation for AI assistants. Generate images and videos, and use 20+ editing tools (background remove/replace, inpainting, object eraser, relight, virtual try-on) dir

Advertise