What is nanobanana-mcp-server CLAUDE.md?

A set of project instructions for a local server that generates and edits images with Google Gemini models through MCP, a way for software tools to communicate with AI services. It documents the project structure, setup, commands, and image-model integration.

Use it when developing, configuring, or troubleshooting this image-generation server and its Gemini integrations.

It gives a coding agent the project-specific information needed to work on the server consistently. Without it, the agent would have to infer setup and development rules from the code.

How qso/nanobanana-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to qso/nanobanana-mcp-server. 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/qso/nanobanana-mcp-server/main/CLAUDE.md

Clone the repo

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

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/qso/nanobanana-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/qso/nanobanana-mcp-server/claude-md)

Your own site

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

Per session 3,030 This file is loaded in full into every session.

When invoked 3,030 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 100% copy Near-identical to another mod 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	$0.03030	$0.03030
Opus 5	$0.01515	$0.01515
Sonnet 5	$0.00606	$0.00606
Haiku 4.5	$0.00303	$0.00303

Measured 9d ago against content hash f63bd77164a1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

nanobanana-mcp-server 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 9d 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.

Origin

This is a copy

100% identical to nanobanana-mcp-server CLAUDE.md — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CLAUDE.md · 349 lines

How it starts

The opening of the file, as written. The whole thing — 349 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

This repository contains a production-ready Nano Banana MCP Server - an AI-powered image generation and editing server that leverages Google's Gemini models through the FastMCP framework. The codebase implements a complete MCP (Model Context Protocol) server with modular architecture, comprehensive error handling, and production-ready features.

⭐ NEW: Nano Banana Pro Integration

The server now supports Gemini 3 Pro Image (Google's latest and most advanced image generation model) alongside the existing Gemini 2.5 Flash Image model:

Key Capabilities:

🏆 4K Resolution: Up to 3840px professional-grade outputs
🌐 Google Search Grounding: Real-world knowledge integration for factual accuracy
🧠 Advanced Reasoning: Configurable thinking levels (LOW/HIGH) for complex compositions
📐 Media Resolution Control: Fine-grained vision processing tuning
🤖 Intelligent Model Selection: Automatic routing based on prompt analysis

Architecture Enhancement:

ModelSelector: New service for intelligent model routing and selection logic
ProImageService: Dedicated service for Gemini 3 Pro Image operations
Multi-tier configuration: ModelSelectionConfig, ProImageConfig alongside existing GeminiConfig

Development Commands

Environment Setup

# Using uv (recommended)
uv sync

# Set up environment
cp .env.example .env
# Edit .env to add your GEMINI_API_KEY

Running the Server

# FastMCP CLI (recommended for development)
# Note: Use mcp_dev.py wrapper to resolve relative import issues
fastmcp dev mcp_dev.py:app

# Direct Python execution
python -m nanobanana_mcp_server.server

# HTTP transport mode
FASTMCP_TRANSPORT=http python -m nanobanana_mcp_server.server

Development Workflow

# Start development server (clean startup)
./scripts/cleanup-ports.sh && fastmcp dev nanobanana_mcp_server.server:create_app

# Code formatting and linting
ruff format .
ruff check .

# Type checking
mypy .

# Run tests
pytest
pytest --cov=. --cov-report=html

# Run specific test categories
pytest -m unit
pytest -m integration

Read the full file on GitHub · 349 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.

9d ago First seen · 349 lines · 3,030 tokens per session scan A f63bd77164a1

Subscribe to this mod's changes

nanobanana-mcp-server CLAUDE.md is an instructions file published in the GitHub repository qso/nanobanana-mcp-server (0 stars, last pushed 7mo ago), licensed MIT. It adds 3,030 tokens to every session, about $0.0152 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to nanobanana-mcp-server CLAUDE.md, differing in 0 lines, and is treated as a copy.

Creative and media

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

nanobanana-mcp-server: Instructions file for Claude Code