What is mcp-image-gen CLAUDE.md?

Development instructions for an MCP server that generates images with Google Gemini and Imagen. MCP is a standard way for an AI assistant to call external tools.

Use it when developing or maintaining the image-generation server, including image creation, editing, and upscaling where supported.

It records the project structure, model-routing rules, setup commands, and common provider mistakes in one place.

How kevinten-ai/mcp-image-gen configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to kevinten-ai/mcp-image-gen. 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/kevinten-ai/mcp-image-gen/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/kevinten-ai/mcp-image-gen

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/kevinten-ai/mcp-image-gen/claude-md/github.svg)](https://agentmods.dev/instructions/kevinten-ai/mcp-image-gen/claude-md)

Your own site

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

Per session 377 This file is loaded in full into every session.

When invoked 377 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	$0.00377	$0.00377
Opus 5.5	$0.00151	$0.00151
Sonnet 5.5	$0.00075	$0.00075
Haiku 4.5	$0.00038	$0.00038

Measured 2mo ago against content hash 25ae35b618d7, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-image-gen 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 · 35 lines

What it actually says

CLAUDE.md — mcp-image-gen

Project Overview

MCP server for AI image generation via Google Gemini and Imagen. Tools include generate_image, plus Vertex-only edit_image and upscale_image, with dynamic model selection per request.

Architecture

Entry: src/image_gen/__init__.py → server.main() via asyncio
Core: src/image_gen/server.py — all logic in one file
Two API patterns: Imagen models use Vertex AI Predict API, Gemini models use GenerateContent API. Routing is automatic based on model name prefix (imagen* → predict).

Key Design Decisions

model parameter is optional on the tool — defaults to GEMINI_MODEL env var
Model catalog (MODELS dict) drives both tool schema enum and resource content
MCP Resources (guide://models, guide://providers) provide AI assistants with selection guidance
On 429 errors, the response auto-suggests switching to an alternative model

Development

uv sync                    # basic deps
uv sync --extra vertex     # with Vertex AI / google-auth
uv run image-gen           # run server

Common Pitfalls

Imagen models are Vertex AI only — don't use imagen-* with the ai-studio provider
New generation defaults should use GA Gemini image model IDs, not expired *-preview IDs
Each model has independent API quota — 429 on one model doesn't mean all are blocked
Two kinds of 429: "quota exceeded" (rate limit) vs "spending cap" (billing limit) — different fixes
Vertex AI default QPM quota is very low (~5). Request increase via GCP Console.

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 · 35 lines · 377 tokens per session scan A 25ae35b618d7

Subscribe to this mod's changes

mcp-image-gen CLAUDE.md is an instructions file published in the GitHub repository kevinten-ai/mcp-image-gen (2 stars, last pushed 3mo ago), licensed MIT. It adds 377 tokens to every session, about $0.0015 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 2026-08-31.

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

mcp-image-gen CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-image-gen CLAUDE.mdkevinten-ai/mcp-image-gen	Instructions file	2	3mo ago	MIT	A	377	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	144k	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,685	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	281k	yesterday	MIT	A	4,335	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,086	GitHub Copilot

mcp-image-gen: Instructions file for Claude Code