What is nano-banana-mcp AGENTS.md?

A set of repository instructions for nano-banana-mcp, an MCP server that generates images through Google Vertex AI. It explains the project layout, commands, coding style, and testing expectations.

Use it when developing, building, testing, or reviewing changes in the nano-banana-mcp repository.

It gives a coding agent the project-specific rules needed to make safe, consistent changes. It also identifies generated files that should not be edited directly.

How fahmidme/nano-banana-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to fahmidme/nano-banana-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/fahmidme/nano-banana-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/fahmidme/nano-banana-mcp

Made for: Codex, OpenCode.

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/fahmidme/nano-banana-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/fahmidme/nano-banana-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/fahmidme/nano-banana-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fahmidme/nano-banana-mcp/agents-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/fahmidme/nano-banana-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/fahmidme/nano-banana-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 653 This file is loaded in full into every session.

When invoked 653 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	$0.00653	$0.00653
Opus 5	$0.00327	$0.00327
Sonnet 5	$0.00131	$0.00131
Haiku 4.5	$0.00065	$0.00065

Measured 12d ago against content hash f4c84e4f54d4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nano-banana-mcp AGENTS.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 12d 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.

AGENTS.md · 39 lines

How it starts

The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Guidelines

This project is an MCP server that generates images with Gemini 3 Pro Image on Vertex AI and can produce true transparent PNGs. This guide covers structure, workflows, and expectations for changes.

Project Structure & Module Organization

src/index.ts is the MCP server entrypoint (tool schema, auth, GCS uploads, Vertex calls, and transparency workflows).
dist/ is the compiled output from TypeScript; treat it as build artifacts and do not edit by hand.
public/ and architecture.png hold static docs/assets.
tmp/ is gitignored scratch output for local experiments.
.env.example documents runtime configuration; .env is local-only.

Build, Test, and Development Commands

npm install installs dependencies.
npm run dev starts the TypeScript entrypoint with tsx for local development.
npm run build compiles src/ into dist/ via tsc.
npm start runs the compiled server from dist/index.js (use after npm run build).

Coding Style & Naming Conventions

TypeScript (ESM) with strict mode enabled (tsconfig.json).
Indentation is 2 spaces; keep line wrapping consistent with existing files.
Use camelCase for variables/functions, PascalCase for types, and UPPER_SNAKE_CASE for env vars.
Keep new logic close to the relevant tool handler in src/index.ts and prefer small helper functions.

Testing Guidelines

No automated test suite is currently defined.
For risky changes, document manual verification steps in the PR (e.g., run npm run dev and invoke the MCP tool with a sample payload).

Commit & Pull Request Guidelines

Commit messages are short, imperative, and sentence-case (examples in history: "Update README...", "Add GCS bucket...").
PRs should include: a concise summary, testing notes (commands run or manual checks), and any config changes (e.g., new env vars in .env.example).

Configuration & Security Notes

Required env vars include GOOGLE_SERVICE_ACCOUNT_JSON and, when needed, NANO_BANANA_GCS_BUCKET.
Long-running tool calls can emit progress heartbeats via NANO_BANANA_PROGRESS_INTERVAL_MS (set 0 to disable).
Task mode is backed by an in-memory task store; task state is lost on server restart.
Transparency defaults are controlled via NANO_BANANA_TRANSPARENCY_KEY_COLOR, NANO_BANANA_TRANSPARENCY_TOLERANCE, and NANO_BANANA_TRANSPARENCY_FEATHER.
IMG.LY background removal can be configured via NANO_BANANA_IMGLY_MODEL, NANO_BANANA_IMGLY_OUTPUT_FORMAT, NANO_BANANA_IMGLY_OUTPUT_QUALITY, and NANO_BANANA_IMGLY_PUBLIC_PATH.
Never commit real service account JSON or .env; update .env.example when adding new settings.

Read the full file on GitHub · 39 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.

12d ago First seen · 39 lines · 653 tokens per session scan A f4c84e4f54d4

Subscribe to this mod's changes

nano-banana-mcp AGENTS.md is an instructions file published in the GitHub repository fahmidme/nano-banana-mcp (9 stars, last pushed 7mo ago), licensed Unlicense. It adds 653 tokens to every session, about $0.0033 per session on Opus 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 2026-08-31.

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

nano-banana-mcp: Instructions file for Codex