Equallogic

Codex Image MCP — AI skill for Claude Code

AI community

Generate images in Claude Code using the ChatGPT subscription you already pay for.

How to install Codex Image MCP

This entry records only its repository, not the path inside it, so there is no exact command to give. Open Equallogic/codex-image-mcp and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Codex Image MCP does

Generate images in Claude Code using the ChatGPT subscription you already pay for. An MCP server for OpenAI's gpt-image-2 via the Codex CLI bundled in ChatGPT.app — no API key, no credits, no third-party service.

Alternatives in AI

System Prompts Leaks — Extracted system prompts from ChatGPT (GPT-5.4, GPT-5.3, Codex), Claude (Opus 4.6, Sonnet 4.6, Claude Code), G 38.6k ★
Vibeproxy — Native macOS menu bar app to use your Claude Code & ChatGPT subscriptions with AI coding tools - no API keys n 3.3k ★
Proxypal — A desktop app that lets you use your AI subscriptions (Claude, ChatGPT, Gemini, GitHub Copilot) with any codin 1.2k ★

README

![codex-image-mcp — image generation in Claude Code, paid for by the ChatGPT subscription you already have](samples/social-preview.png)

codex-image-mcp

No API key. No credits. No third-party service holding your prompts. This is an MCP server that drives the Codex CLI already bundled inside ChatGPT.app, which authenticates from your own `~/.codex/auth.json` and calls OpenAI's built-in `gpt-image-2`. Every image on this page, banner included, came out of the tool while I was building it.

Why I built it

I wanted Claude to make images for me. Every option was wrong. The hosted MCP servers — Pixa, ImagineArt, Claude Imagine — are someone else's service with a credit tier attached. The OpenAI-key servers bill you per image for a model your subscription already covers. Local diffusion on a 16 GB M1 Pro is slow and nowhere near `gpt-image-2` on quality.

Then I noticed my ChatGPT app ships a full Codex binary, that Codex has image generation switched on by default, and that it signs in as me. The bridge turned out to be one command. Getting that command to behave took considerably longer, and the rest of this README is what went wrong along the way.

Install

You need the ChatGPT desktop app and a logged-in Codex session. Then:

git clone https://github.com/Equallogic/codex-image-mcp.git
cd codex-image-mcp && npm install
claude mcp add --scope user codex-image -- node "$(pwd)/server.js"

Restart Claude Code. One tool appears:

generate_image(prompt, output_path, [reference_images])

It writes the file and hands back the path, format, dimensions, elapsed time and tokens spent. Roughly 45 seconds an image.

What I learned making it reliable

This is the part worth reading, because all three of these cost me real money to find out.

**Phrasing decides whether you get an image at all.** Ask for "Generate an image: X. Just generate the image." and Codex replies with the image tool's own prompt-writing guidance instead of calling it. Seventy-ei