gemini-image-mcp: Instructions file for Claude Code

CLAUDE.md

gemini-image-mcp CLAUDE.md is an instructions file for Claude Code from someshwarpatil/gemini-image-mcp. It costs 750 tokens per session, scanned A, original, MIT.

Instructions for a Python MCP server that lets Claude Code generate and edit images with Google Gemini image models through Vertex AI, Google Cloud’s managed AI platform.

In plain words
What is it for?
It helps contributors install, run, format, and authenticate the image server, using the specified Gemini and Imagen model aliases.
Why use it?
It clarifies the supported models, Python workflow, and required Google Cloud authentication so the server is used as configured.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is someshwarpatil/gemini-image-mcp's own configuration. It tells Claude Code how to work on gemini-image-mcp itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything gemini-image-mcp configures →

Reuse

Borrowing it

Nothing to install: this file belongs to someshwarpatil/gemini-image-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/someshwarpatil/gemini-image-mcp/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/someshwarpatil/gemini-image-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.

agentmods badge for gemini-image-mcp CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/someshwarpatil/gemini-image-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/someshwarpatil/gemini-image-mcp/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/someshwarpatil/gemini-image-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/someshwarpatil/gemini-image-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.

agentmods 80×15 button for gemini-image-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/someshwarpatil/gemini-image-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/someshwarpatil/gemini-image-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 750 This file is loaded in full into every session.
When invoked 750 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00750 $0.00750
Opus 5 $0.00375 $0.00375
Sonnet 5 $0.00150 $0.00150
Haiku 4.5 $0.00075 $0.00075

Measured 10d ago against content hash 93967b00ea1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

gemini-image-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 10d 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 · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — gemini-image-mcp

Guide for working inside this repo with Claude Code (or for any contributor).

What this is

A standalone, user-scoped MCP server (stdio, official Python MCP SDK / FastMCP) that lets Claude Code generate and edit images via Google's Gemini image models on Vertex AI. Default model is Nano Banana (gemini-2.5-flash-image); also exposes Nano Banana Pro (gemini-3-pro-image-preview, preview) and the Imagen 4 family, behind friendly aliases.

Conventions

  • Python 3.12 + uv. Never bare pip. uv sync, uv run …, uv add ….
  • Lint/format with ruff: uv run ruff check --fix and uv run ruff format.
  • Conventional commits (feat:, fix:, chore:), small and reviewable.
  • src-layout: package at src/gemini_image_mcp/, console script gemini-image-mcpgemini_image_mcp.server:main.

Auth — Vertex + ADC ONLY

  • genai.Client(vertexai=True, project=…, location=…). No API key. No JSON key file. ADC (gcloud auth application-default login) is the only auth path.
  • The GCP project is read from GOOGLE_CLOUD_PROJECT; when unset the SDK auto-detects it from ADC / gcloud config. No project id is baked into the source.

Model ids are pinned — do NOT invent

The alias → model-id map in models.py uses exact, verified Vertex ids. Do not "modernize", guess, or reformat them. If a GA Vertex id for Nano Banana Pro ships later, swap it in models.py (one-line change) — don't fabricate one.

Location split (important)

  • Gemini image models are global-only on Vertex → GOOGLE_CLOUD_LOCATION=global.
  • Imagen is regional → separate client pinned to us-central1 (GEMINI_IMAGE_IMAGEN_LOCATION).

Two cached genai.Client instances in gemini_client.py, one per location. A single location cannot serve both surfaces.

Output handling

Always save the full-res PNG to disk and always return its absolute path. Return the downscaled preview Image block only when return_image=True. output_dir order: explicit arg → GEMINI_IMAGE_OUTPUT_DIR → process CWD (the server can't see the client's scratchpad — it's a separate process).

Read the full file on GitHub · 69 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.

  1. 10d ago First seen · 69 lines · 750 tokens per session scan A 93967b00ea1a

Subscribe to this mod's changes

gemini-image-mcp CLAUDE.md is an instructions file published in the GitHub repository someshwarpatil/gemini-image-mcp (1 stars, last pushed 2mo ago), licensed MIT. It adds 750 tokens to every session, about $0.0037 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.

Related

Other instructions, from other repositories

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens