Summary
Plugs Claude directly into Google's Gemini image generation API, specifically the Nano Banana and Nano Banana Pro models. You get five tools over stdio: list available models, generate images from text prompts, edit or compose existing images with instructions, batch generate consistent image sets from a master prompt, and run multi-turn refinement sessions via the Interactions API. Images land on disk by default with paths returned, or you can pull them inline as base64. Requires a Gemini API key and runs through the generativelanguage.googleapis.com v1beta endpoint. Reach for this when you need Claude to generate or iterate on images without leaving the MCP context.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
gemini-mcp
MCP server for Google Gemini image generation and editing. Exposes four tools to Claude over stdio: list available models, generate images from text prompts, edit or compose images with text instructions, and generate a consistent set of images from a master prompt. Images are written to disk by default (path returned) or returned inline as base64. Built on the Gemini v1beta API (generativelanguage.googleapis.com) using the Nano Banana / Nano Banana Pro model family.
Developed and maintained by AI (Claude Code).
Environment Variables
| Variable | Required | Description |
|---|---|---|
GEMINI_API_KEY | Yes | Your Google Gemini API key (aistudio.google.com/apikey) |
GEMINI_IMAGE_MODEL | No | Override the default image model (default: gemini-3-pro-image) |
GEMINI_OUTPUT_DIR | No | Default directory for generated images (default: current working directory) |
GEMINI_INPUT_DIR | No | Directory to resolve bare input-image filenames against (so images: ["foo.jpg"] works) |
Tools
| Tool | Description |
|---|---|
gemini_list_models | List available Gemini image models and the current default |
gemini_generate_image | Generate image(s) from a text prompt |
gemini_edit_image | Edit or compose one or more input images with a text instruction |
gemini_generate_set | Generate a master image plus N consistent images referencing it |
gemini_interact | Multi-turn generation/editing via the Interactions API (Beta); returns an interaction_id to refine the same image conversationally |
Quick Start
{
"mcpServers": {
"gemini": {
"command": "npx",
"args": ["-y", "@chrischall/gemini-mcp"],
"env": {
"GEMINI_API_KEY": "your-api-key-here"
}
}
}
}
See SKILL.md for full usage documentation.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →Configuration
GEMINI_API_KEY*secretYour Google Gemini API key (aistudio.google.com/apikey)
GEMINI_IMAGE_MODELOverride the default image model (default: gemini-3-pro-image)
GEMINI_OUTPUT_DIRDefault directory for generated images (default: current working directory)
GEMINI_INPUT_DIRDirectory to resolve bare input-image filenames against
Categories
Registryactive
Package@chrischall/gemini-mcp
TransportSTDIO
AuthRequired
UpdatedJun 10, 2026
