# Nano-Banana (Gemini 2.5 Flash Image)

> Use this tool when you need to generate and edit images using Google's Gemini 2.5 Flash Image technology, creating new images from text prompts or refining existing ones with optional reference images. It solves problems of visual content creation and iterative refinement for AI assistants, accepting text prompts and reference images as inputs and producing edited images as outputs. Ideal for use cases requiring cross-platform image generation and editing capabilities with session-based tracking and configuration management.

Canonical page: https://skillsregistry.net/skills/conechoai-nano-banana  
JSON: https://api.skillsregistry.net/v1/skills/conechoai-nano-banana

## Description

This MCP server provides access to Google's Gemini 2.5 Flash Image generation and editing capabilities through a TypeScript implementation that supports both creating new images from text prompts and editing existing images with optional reference images. Built with cross-platform support, it handles configuration through environment variables or local config files, automatically manages image saving to platform-appropriate directories (Documents on Windows, current directory on macOS/Linux), and includes session-based image tracking for iterative editing workflows. The implementation offers six core tools including token configuration, image generation, image editing with multi-image support, continuation editing for the last generated image, and status checking, making it suitable for AI assistants that need to create and iteratively refine visual content using Google's latest image generation technology.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/conechoai-nano-banana)
- **Repository:** <https://github.com/conechoai/nano-banana-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "conechoai-nano-banana"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/conechoai-nano-banana` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/conechoai-nano-banana/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt