Image generation with Google Gemini Nano Banana 2 via MCP
MCP server for Google Gemini image generation, upgraded for Nano Banana 2 (gemini-3.1-flash-image-preview).
A fork/rewrite of ConechoAI/Nano-Banana-MCP with:
Get one from Google AI Studio.
Via Claude Code plugin (recommended):
claude plugin add nano-banana-2-mcp
Or manually via npx — add to your Claude Code MCP settings:
{
"mcpServers": {
"nano-banana-2": {
"command": "npx",
"args": ["-y", "nano-banana-2-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}
Or from source for development:
git clone https://github.com/daveremy/nano-banana-2-mcp.git
cd nano-banana-2-mcp
npm install
npm run build
Then point your MCP config at dist/index.js:
{
"mcpServers": {
"nano-banana-2": {
"command": "node",
"args": ["/path/to/nano-banana-2-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}
The tools will be available after restart.
generate_imageGenerate a new image from a text prompt.
| Parameter | Type | Default | Description |
|---|---|---|---|
prompt | string | (required) | Text prompt for the image |
aspectRatio | string | "1:1" | Aspect ratio (e.g. "16:9", "9:16") |
resolution | string | "1K" | 1K, 2K, or 4K |
thinking | string | "minimal" | minimal or high |
numberOfImages | number | 1 | 1–4 |
returnInlineImage | boolean | true | If false, return only file path |
edit_imageEdit an existing image file.
Same parameters as generate_image, plus:
| Parameter | Type | Description |
|---|---|---|
imagePath | string | (required) Path to the image to edit |
referenceImages | string[] | Optional additional reference images |
continue_editingContinue editing the last generated/edited image. Same parameters as edit_image minus imagePath (uses the last image automatically).
get_configuration_statusCheck API key, active model, and settings.
get_last_image_infoGet path and size of the last generated image.
| Variable | Default | Description |
|---|---|---|
GEMINI_API_KEY | (required) | Google Gemini API key |
NANO_BANANA_MODEL | gemini-3.1-flash-image-preview | Model ID override |
NANO_BANANA_OUTPUT_DIR | ./generated_imgs | Image save directory |
NANO_BANANA_INLINE_IMAGE | true | Default for returnInlineImage |
The server auto-detects model capabilities:
*-image, *-image-preview): get imageConfig (resolution, aspect ratio)thinkingConfigThis means you can use NANO_BANANA_MODEL=gemini-2.5-flash-image and it will send imageConfig but skip thinkingConfig.
This repo includes a Claude Code plugin with a generate-image skill that provides best-practice prompting guidance. Install via claude plugin add nano-banana-2-mcp or add the repo path to your Claude Code plugins config.
See CONTRIBUTING.md for development setup, testing, and release process.
Based on ConechoAI/Nano-Banana-MCP (MIT License).
MIT
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
npx claudepluginhub envision-construction/envision-claude-marketplace --plugin nano-banana-2Memory compression system for Claude Code - persist context across sessions
Standalone image generation plugin using Nano Banana MCP server. Generates and edits images, icons, diagrams, patterns, and visual assets via Gemini image models. No Gemini CLI dependency required.
Streamline people operations — recruiting, onboarding, performance reviews, compensation analysis, and policy guidance. Maintain compliance and keep your team running smoothly.
Write feature specs, plan roadmaps, and synthesize user research faster. Keep stakeholders updated and stay ahead of the competitive landscape.
Create content, plan campaigns, and analyze performance across marketing channels. Maintain brand voice consistency, track competitors, and report on what's working.
Prospect, craft outreach, and build deal strategy faster. Prep for calls, manage your pipeline, and write personalized messaging that moves deals forward.