What is nanobanana-mcp CLAUDE.md?

Project instructions for NanoBanana MCP, a server that lets Claude use Google Gemini to generate, edit, and analyse images. They describe the project, its commands, architecture, and available tools.

Installing dependencies, building, running, and developing NanoBanana MCP. They also document image generation, image editing, image analysis, model selection, and aspect-ratio settings.

They give an AI coding assistant the context needed to work on the repository without guessing how it is built or what its tools do.

How YCSE/nanobanana-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to YCSE/nanobanana-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/YCSE/nanobanana-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/YCSE/nanobanana-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ycse/nanobanana-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/ycse/nanobanana-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/ycse/nanobanana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ycse/nanobanana-mcp/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ycse/nanobanana-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/ycse/nanobanana-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 923 This file is loaded in full into every session.

When invoked 923 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00923	$0.00923
Opus 5.5	$0.00369	$0.00369
Sonnet 5.5	$0.00185	$0.00185
Haiku 4.5	$0.00092	$0.00092

Measured 2mo ago against content hash b02c7a7eaf84, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

nanobanana-mcp CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Project Overview

NanoBanana MCP is a Model Context Protocol server that enables Claude Desktop/Code to use Google Gemini's multimodal capabilities for image generation, editing, and vision analysis.

Build Commands

npm install          # Install dependencies
npm run build        # Compile TypeScript to dist/
npm run dev          # Development mode with hot reload (tsx watch)
npm run start        # Run compiled server

Architecture

Single-file MCP server (src/index.ts) using stdio transport:

MCP SDK Integration: Uses @modelcontextprotocol/sdk for server/transport
Dual Gemini SDKs:
- @google/generative-ai (genAI) - For chat operations
- @google/genai (genAINew) - For image generation/editing with streaming

Tools Exposed

Tool	Model	Purpose
`set_aspect_ratio`	N/A	Required before image generation/editing. Set aspect ratio for session
`set_model`	N/A	Switch between flash/pro models at runtime
`gemini_chat`	configurable	Multi-turn conversation with up to 10 images
`gemini_generate_image`	configurable	2K image generation with consistency support
`gemini_edit_image`	configurable	Image editing via natural language
`get_image_history`	N/A	View session image history
`clear_conversation`	N/A	Reset conversation context

Aspect Ratio (Required)

Valid values: 1:1, 9:16, 16:9, 3:4, 4:3, 3:2, 2:3, 5:4, 4:5, 21:9

Must call set_aspect_ratio before gemini_generate_image or gemini_edit_image. No default value - returns error if not set.

Runtime Model Selection

Use set_model tool to switch models per-session without restarting:

model="flash" → gemini-3.1-flash-image-preview (faster, default)
model="pro" → gemini-3-pro-image-preview (higher quality)

Slash Commands:

Claude Code: cp commands/claude-code/*.md ~/.claude/commands/
Cursor: cp commands/cursor/*.md ~/.cursor/commands/
/nb-flash - Switch to Flash model
/nb-pro - Switch to Pro model

Read the full file on GitHub · 94 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 94 lines · 923 tokens per session scan A b02c7a7eaf84

Subscribe to this mod's changes

nanobanana-mcp CLAUDE.md is an instructions file published in the GitHub repository YCSE/nanobanana-mcp (32 stars, last pushed 8mo ago), licensed MIT. It adds 923 tokens to every session, about $0.0037 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Creative and media ai claude claude-desktop gemini google-ai image-generation

nanobanana-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
nanobanana-mcp CLAUDE.mdYCSE/nanobanana-mcp	Instructions file	32	8mo ago	MIT	A	923	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode ai-customization.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	1,907	GitHub Copilot

nanobanana-mcp: Instructions file for Claude Code