What is the GPT-Image-1 MCP Server?

The GPT-Image-1 MCP Server is a Model Context Protocol (MCP) server that allows you to generate and edit images using the OpenAI gpt-image-1 model.

What is MCP?

MCP stands for Model Context Protocol. It is an open protocol that standardizes how applications provide context to LLMs, enabling seamless integration and communication.

What are the prerequisites for using the GPT-Image-1 MCP Server?

You need Node.js (v14 or higher) and an OpenAI API key with access to the gpt-image-1 model.

How do I install the GPT-Image-1 MCP Server?

You can run it directly using NPX with the command: npx -y @cloudwerxlab/gpt-image-1-mcp.

What environment variables do I need to configure?

You need to set the OPENAI_API_KEY with your OpenAI API key. Optionally, you can set GPT_IMAGE_OUTPUT_DIR to specify a custom directory for saving generated images.

Which MCP clients are compatible with the GPT-Image-1 MCP Server?

The server is compatible with VS Code MCP Extension, Roo, Cursor, Augment, and Windsurf.

How do I configure the server in my MCP client?

You need to add a configuration block to the mcpServers object in your client’s settings file, specifying the command, arguments, and environment variables.

What are the main tools available in the GPT-Image-1 MCP Server?

The server provides create_image for generating new images from text prompts and create_image_edit for editing existing images with text prompts and masks.

Where are the generated images saved by default?

By default, images are saved in the user’s Pictures folder under the gpt-image-1 subfolder. You can customize this location using the GPT_IMAGE_OUTPUT_DIR environment variable.

What should I do if I encounter MIME type errors?

Ensure that your image files have the correct extension (.png, .jpg, etc.) that matches their actual format.

What if I get an API key error?

Verify that your OpenAI API key is correct and has access to the gpt-image-1 model.

Where can I report bugs or request features?

You can report bugs or request features on the project’s GitHub issues page.