What is create-image-mcp CLAUDE.md?

Development instructions for an MCP server that creates images from text using OpenAI’s GPT Image model. MCP is a standard way for AI assistants to call external tools.

Running, developing, and testing an image-generation server for Claude Desktop, Claude Code, or another MCP client.

It gives an AI assistant a documented way to request generated images and provides commands for running and testing the server.

How gregpriday/create-image-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to gregpriday/create-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/gregpriday/create-image-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/gregpriday/create-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/gregpriday/create-image-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/gregpriday/create-image-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/gregpriday/create-image-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/gregpriday/create-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.

Your own site · 80×15

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

Per session 2,006 This file is loaded in full into every session.

When invoked 2,006 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	$0.02006	$0.02006
Opus 5.5	$0.00802	$0.00802
Sonnet 5.5	$0.00401	$0.00401
Haiku 4.5	$0.00201	$0.00201

Measured 1mo ago against content hash 2087aff1a089, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

create-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 1mo 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 · 141 lines

How it starts

The opening of the file, as written. The whole thing — 141 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 is a Model Context Protocol (MCP) server that generates and edits images using OpenAI's GPT Image 2.5 models (gpt-image-2.5-sunburst default, gpt-image-2.5-flare fast). It enables Claude Desktop, Claude Code, and other MCP clients to create images from text descriptions.

Key Technologies:

MCP SDK (@modelcontextprotocol/sdk) for stdio server transport and JSON-RPC 2.0 communication
OpenAI SDK (openai) for GPT Image generation API
Node.js native test runner for unit/integration testing
ES modules (type: "module" in package.json)

Development Commands

Running the Server

npm start                    # Start MCP server (runs check-env first)
npm run dev                  # Auto-reload mode with --watch flag

Testing

npm test                     # Unit tests only (test/unit/**/*.test.js)
npm run test:integration     # MCP stdio protocol test (add CREATE_IMAGE_LIVE_TEST=1 for a paid live generation)
npm run test:all             # All tests (unit + integration)

Running a single test file:

node --test test/unit/tool-handler.test.js

Environment & Security

npm run check-env            # Validate .env configuration
npm run security:audit       # Check for vulnerabilities
npm run security:fix         # Auto-fix security issues
npm run security:update      # Update deps and audit

Architecture

MCP Server Design

The server implements a single-tool MCP server following the stdio transport pattern:

Server Initialization (src/index.js)
- Creates MCP Server instance with name/version metadata
- Declares tools capability
- Connects to StdioServerTransport for JSON-RPC communication
Tool Registration
- Handles ListToolsRequestSchema to expose the create_image tool
- Tool description is optimized for AI agent invocation with clear trigger phrases
- Input schema includes validation rules and examples

Read the full file on GitHub · 141 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.

1mo ago Changed · +10 lines · +543 tokens per session 2087aff1a089
2mo ago First seen · 131 lines · 1,463 tokens per session scan A a491e402f396

Subscribe to this mod's changes

create-image-mcp CLAUDE.md is an instructions file published in the GitHub repository gregpriday/create-image-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,006 tokens to every session, about $0.0080 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

create-image-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
create-image-mcp CLAUDE.mdgregpriday/create-image-mcp	Instructions file	0	1mo ago	MIT	A	2,006	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	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

create-image-mcp: Instructions file for Claude Code