Nano Banana MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Gemini API key |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| generate_imageC | Generate an image using Gemini image models (Nano Banana 2 or Nano Banana Pro) |
| edit_imageB | Edit an existing image using Gemini image models (Nano Banana 2 or Nano Banana Pro) |
| analyze_imageA | Analyze an image and answer questions about it using Gemini |
| multi_image_editA | Edit or combine multiple images using Gemini image models (e.g., transfer pose, style, combine elements) |
| batch_generateB | Generate multiple images from an array of prompts |
| generate_variationsC | Generate variations of an existing image |
| generate_with_templateB | Generate an image using a pre-defined style template |
| compare_imagesB | Compare two images and analyze their differences or similarities |
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 8 tools
Each tool targets a distinct operation (generate, edit, analyze, compare, batch, variations, template), so boundaries are clear. Minor overlap exists between generate_variations and edit_image, but the descriptions help differentiate the intended use cases.
Tool names follow a consistent snake_case verb-object pattern (generate_image, edit_image, analyze_image, compare_images). A few names like multi_image_edit and batch_generate add modifiers but still fit the overall predictable style.
With 8 tools, the server is well-scoped for an image generation and manipulation domain, covering all major workflows without excessive redundancy or a thin feature set.
The set covers generation, editing, analysis, comparison, batch, variations, and template-based creation, providing comprehensive lifecycle coverage for image tasks. Minor gaps like model management or file export are not essential to the core purpose.