Skip to main content
Glama

KOF Nano Banana MCP Server 🍌

MCP server for Gemini native image generation (Nano Banana). Part of the KeepOnFirst Agentic Workflow.

English | 繁體中文

⚠️ Important: Billing Required

Note: The Gemini API Free Tier does NOT support image generation models. To use this MCP server, you must provide an API key from a Google Cloud project with billing enabled.

Related MCP server: Gemini Image Gen MCP Server

Features

  • Generate images using Gemini 2.5 Flash Image or Gemini 3 Pro Image

  • Process queue of prompt files with validation and dry-run support

  • YAML frontmatter support for prompt configuration

  • Cross-IDE compatible - works with any MCP-enabled client

β˜• Support this project

If this project helps you, you can support development here:

Installation

If you have published this package or use it locally:

{
  "mcpServers": {
    "nanobanana": {
      "command": "npx",
      "args": ["-y", "@keeponfirst/kof-nanobanana-mcp"],
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Option 2: Local Development

cd kof-nanobanana-mcp
npm install
npm run build

Then configure absolute path in your MCP config (see Configuration section).

Configuration

1. Get a Gemini API Key

  1. Go to Google AI Studio

  2. Create an API key

  3. IMPORTANT: Ensure your project has billing enabled. These models are paid-only.

2. Add to MCP Config

Add to your MCP configuration file (e.g., ~/.gemini/antigravity/mcp_config.json):

{
  "servers": {
    "nanobanana": {
      "command": "node",
      "args": ["/path/to/kof-nanobanana-mcp/dist/index.js"],
      "env": {
        "GEMINI_API_KEY": "your-api-key-here"
      }
    }
  }
}

Tools

nanobanana_generate_image

Generate a single image.

Parameters:

Name

Type

Required

Description

prompt

string

βœ…

Image description (10-5000 chars)

output_path

string

βœ…

Path to save the image

model

string

❌

gemini-2.5-flash-image (default) or gemini-3-pro-image-preview

aspect_ratio

string

❌

1:1, 16:9, 9:16, 4:3, 3:4

overwrite

boolean

❌

Overwrite existing file (default: false)

Example:

{
  "prompt": "A modern flat illustration of three AI robots working together on code",
  "output_path": "assets/generated/workflow-hero.png",
  "model": "gemini-2.5-flash-image",
  "aspect_ratio": "16:9"
}

nanobanana_list_queue

List and validate prompt files in the queue.

Parameters:

Name

Type

Required

Description

queue_dir

string

❌

Queue directory (default: nanobanana/queue)

validate

boolean

❌

Validate files (default: true)

check_conflicts

boolean

❌

Check if outputs exist (default: true)

nanobanana_process_queue

Batch process all prompt files.

Parameters:

Name

Type

Required

Description

queue_dir

string

❌

Queue directory (default: nanobanana/queue)

validate_only

boolean

❌

Only validate, no generation

dry_run

boolean

❌

Preview without API calls

overwrite

string

❌

skip, overwrite, or rename

Prompt File Format

Create .md files in nanobanana/queue/ with YAML frontmatter:

---
output_path: assets/generated/workflow-hero.png
model: gemini-2.5-flash-image
aspect_ratio: 16:9
overwrite: false
---

# Workflow Hero Image

Create a modern, sleek hero illustration showing three AI agents
working together in a software development workflow.

## Style Guidelines
- Style: Flat illustration with gradients
- Color palette: Deep purple (#6B46C1) to blue (#3B82F6)
- Background: Subtle gradient

Pricing Reference

Model

Price per Image

Gemini 2.5 Flash Image

~$0.039 (1024x1024)

Gemini 3 Pro Image (2K)

~$0.134

Gemini 3 Pro Image (4K)

~$0.24

License

MIT

Available Tools

3 tools
nanobanana_generate_imageGenerate Image with Nano BananaA
Idempotent

Generate an image using Gemini's native image generation (Nano Banana).

This tool calls the Gemini API to generate an image based on your text prompt and saves it to the specified path.

Models:

  • gemini-2.5-flash-image: Fast, efficient (~$0.039/image)

  • gemini-3-pro-image-preview: Higher quality, supports 4K (~$0.134-0.24/image)

Supported Aspect Ratios: 1:1, 16:9, 9:16, 4:3, 3:4

Example:

prompt: "A modern flat illustration of a workflow diagram with three connected nodes, purple and blue gradient colors, minimal style"
output_path: "assets/generated/workflow-hero.png"
model: "gemini-2.5-flash-image"
aspect_ratio: "16:9"

Inputs: prompt (required), output_path (required), model, aspect_ratio, +1 more.

nanobanana_list_queueList Nano Banana QueueA
Read-onlyIdempotent

List and validate prompt files in the queue directory.

This tool scans the queue directory for markdown prompt files and provides:

  • Validation status for each file

  • Conflict detection (output file already exists)

  • Preview of prompt content

Use this to review what will be generated before running process_queue.

Example:

queue_dir: "nanobanana/queue"
validate: true
check_conflicts: true

Inputs: queue_dir, validate, check_conflicts.

nanobanana_process_queueProcess Nano Banana QueueA

Process all prompt files in the queue directory and generate images.

Modes:

  • validate_only=true: Only validate prompts, no API calls

  • dry_run=true: Show what would be generated, no API calls

  • Both false: Actually generate images

Overwrite Strategies:

  • skip: Skip if output file exists (default)

  • overwrite: Replace existing files

  • rename: Generate with suffix (e.g., hero_1.png)

After successful generation, prompt files are moved to completed_dir with timestamp.

Example:

queue_dir: "nanobanana/queue"
dry_run: true
overwrite: "skip"

Inputs: queue_dir, output_dir, completed_dir, model, +3 more.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose with no overlap: generate_image creates individual images, list_queue inspects pending files, and process_queue batch processes the queue. The descriptions reinforce these separate functions, making misselection unlikely.

    Naming Consistency5/5

    All tools follow a perfect verb_noun pattern with the 'nanobanana_' prefix: generate_image, list_queue, process_queue. This consistent naming convention makes the tool set predictable and easy to understand.

    Tool Count5/5

    Three tools is ideal for this server's focused scope of image generation queue management. Each tool earns its place by covering distinct aspects of the workflow: single generation, queue inspection, and batch processing.

    Completeness4/5

    The tool set covers the core image generation workflow well with generation, inspection, and processing capabilities. A minor gap exists in not providing tools for managing completed images or modifying queue entries, but agents can work around this with file system operations.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      B
      quality
      D
      maintenance
      Enables image generation and multi-turn editing sessions using the Gemini API within MCP-compatible environments. Users can create, modify, and configure images through natural language commands, supporting features like aspect ratio adjustments and session-based image transformations.
      5
      ISC
    • A
      license
      A
      quality
      B
      maintenance
      Enables text-to-image generation and image editing or composition with Google's Gemini image models via MCP tools, prompts, and resources. Supports automatic model selection, aspect ratio and resolution control, curated prompt templates, and three credential modes (Gemini API key, Vertex AI Express Mode, or ADC).
      6
      369 npm
      1
      MIT
    • A
      license
      Not graded
      quality
      A
      maintenance
      Enables assistants in any MCP client to generate new images or edit existing ones, automatically enriching short requests with composition, lighting, and camera details before sending them to Gemini, OpenAI, or BytePlus Seedream. Supports quality presets, aspect ratios, image sizes, character consistency, blended inputs, and Google Search grounding for current information.
      1,781 npm
      MIT