nano-banana-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | API key of Google AI Studio | |
| NANO_BANANA_MODEL | No | Model to use for image generation | gemini-2.5-flash-image |
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 | Genera una imagen a partir de un prompt de texto usando Gemini 2.5 Flash Image (Nano Banana). Devuelve la imagen en base64. |
| edit_imageA | Edita una imagen existente según un prompt (inpainting, cambio de estilo, retoques). La imagen puede ser una ruta a un archivo local, un data URL o base64 crudo. |
| compose_imagesA | Combina varias imágenes en una sola según un prompt (composición, fusión, transferencia de estilo, consistencia de personaje). Cada imagen puede ser ruta local, data URL o base64. |
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 3 tools
Each tool serves a distinct purpose: generate creates from scratch, edit modifies a single existing image, and compose blends multiple images. No overlap or ambiguity in their scopes.
All tool names follow a consistent verb_noun pattern: generate_image, edit_image, compose_images. The pattern is uniform and predictable.
Three tools is a well-scoped set for an image generation server focused on create, edit, and compose operations. Each tool is essential and none are redundant.
The surface covers the core image workflows (generation, editing, composition). Minor gaps like image analysis or format conversion exist, but these are not critical for the primary purpose.