# Nano Banana (Gemini Image Generator)

> Use this tool when you need to generate high-quality images from text prompts and share them instantly via web URLs. It solves problems in content creation, conversation, and application workflows where immediate image accessibility is required. The tool takes text prompts as input and returns publicly accessible image URLs as output, making it ideal for AI assistants that need to create and share images without local file management.

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

## Description

MCP server by GuilhermeAumo that generates images using Google's Gemini 2.5 Flash Image Preview model and automatically uploads them to ImgBB for web hosting. Built with FastMCP and designed around a single generate_image tool, the implementation takes text prompts, uses Gemini's native image generation capabilities to create high-quality images, and returns publicly accessible URLs rather than raw base64 data. The server requires both Gemini API and ImgBB API keys, making it suitable for AI assistants that need to create and share images in conversations, content creation workflows, or applications where generated images need to be immediately accessible via web URLs without local file management.

## Trust

- **Trust score (0–1):** 0.64
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-02

## Source

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

## 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": "nano-banana"
    }
  }
}
```

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