@ramlyburger/gpt-image-2-mcp

Turn any MCP-compatible AI client into an image generator. Send a normal prompt, choose a backend mode, and get real saved image files back.

Popularity

PulseMCP: https://www.pulsemcp.com/servers/ramlyburger-gpt-image-2

🖼️ What It Does

• ✍️ Prompt in: ask for an image from your MCP client.
• ⚙️ MCP server runs: gpt-image-2-mcp handles the image request.
• 💾 Files out: every result includes output_dir, image_path, and metadata.
• 🔐 No ChatGPT API key needed in chatgpt-web mode. You only need a ChatGPT account and a successful sign-in at chatgpt.com.

🚀 Quick Start

Add the server to your MCP client:

{
  "mcpServers": {
    "gpt-image-2": {
      "command": "npx",
      "args": ["-y", "@ramlyburger/gpt-image-2-mcp"],
      "env": {
        "GPT_IMAGE_BACKEND": "chatgpt-web"
      }
    }
  }
}

That is enough for the ChatGPT website mode. The first run opens ChatGPT so you can sign in or complete verification. After that, the local profile can be reused across restarts.

For direct API generation, set OPENAI_API_KEY and change GPT_IMAGE_BACKEND to api.

🧭 Pick A Mode

Mode	What you need	Best when	Notes
chatgpt-web	A ChatGPT account and sign-in at chatgpt.com	You want a simple setup without a ChatGPT API key	Good beginner default
api	OPENAI_API_KEY	You want the direct API path	Uses gpt-image-2
auto	Preferably an API key; otherwise a usable ChatGPT website session	You want API first with fallback behavior	Tries API first, then falls back only when the API backend is unavailable

🎬 Demo

Click the GIF to open the full MP4.

🧰 Tool Surface

• generate_image(prompt, backend?, n?, size?, quality?, output_format?, conversation_mode?, timeout_seconds?)
• backend_status(backend?)
• browser_visibility(action?, start_browser?)

Backend values are api, chatgpt-web, or auto.

Use conversation_mode="new" or conversation_mode="continue" with the ChatGPT website mode.

📄 Technical Reference

The section below is the implementation-oriented view.

Figure 1. System Model

flowchart LR
    A["MCP client"] --> B["gpt-image-2-mcpstdio server"]
    B --> C["Input validationZod schemas"]
    C --> D{"Backend selection"}
    D --> E["OpenAI API mode"]
    D --> F["ChatGPT website mode"]
    E --> G["Saved image filesmetadata.json"]
    F --> G

Abstract

gpt-image-2-mcp is a small TypeScript MCP server that exposes image generation through a narrow tool contract. The server validates MCP tool input, resolves the requested backend, persists generated artifacts to disk, and returns structured metadata plus image content to the caller.

Method

The implementation follows a five-stage pipeline:

1. parse and validate MCP tool input
2. resolve the backend from api, chatgpt-web, or auto
3. execute the selected image-generation path
4. write generated images and metadata.json to a prompt-derived output directory
5. return output_dir, image_path, images, and backend metadata

The auto mode attempts the API backend first and falls back to chatgpt-web only when the API backend is unavailable.

Artifact Model