Nano Banana MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | No | Gemini API key; if provided, skips OAuth and uses this key. | |
| NANO_BANANA_CLIENT_ID | No | Override embedded OAuth client ID. | |
| NANO_BANANA_CONFIG_DIR | No | Custom config directory. | |
| NANO_BANANA_OUTPUT_DIR | No | Custom image output directory. | |
| NANO_BANANA_CLIENT_SECRET | No | Override embedded OAuth client secret. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageA | Create a new image from a text prompt using Google Gemini image models. Returns the file path of the saved image. |
| edit_imageA | Edit an existing image using a text prompt. Optionally provide reference images for style guidance. Returns the file path of the saved result. |
| continue_editingA | Refine the last generated or edited image with a new prompt. Must call generate_image or edit_image first. Returns the file path of the saved result. |
| configure_authA | Set a Gemini API key for authentication. Get your key from Google AI Studio (https://aistudio.google.com/apikey). |
| get_statusA | Check current authentication state, active model, and image output directory. Use this to verify setup before generating images. |
| get_last_imageA | Get metadata about the most recently generated or edited image, including file path, MIME type, timestamp, and size. |
| list_modelsA | List all available Gemini image models with their product name, ID, and whether they are the default. Use model IDs when calling generate_image, edit_image, or continue_editing. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool has a distinct role, but edit_image and continue_editing both modify an image based on a prompt, so an agent might briefly hesitate between them. The dependency note on continue_editing and the 'existing image' wording in edit_image reduces but does not eliminate this overlap.
All tool names use a consistent snake_case verb-first pattern: list_models, generate_image, edit_image, configure_auth, get_status, get_last_image. continue_editing fits the same pattern despite using a gerund rather than a simple noun.
Seven tools is well-scoped for a focused image-generation/editing server. Each tool covers a necessary part of the workflow without redundancy or bloat.
The surface covers authentication, model discovery, generation, editing, iterative refinement, status checking, and access to the latest output metadata. There are no obvious dead ends; model selection is handled via parameters, and image files are returned as paths.