create-imageLABSCO SUMMARY
Editing is the half that matters, and most image wrappers skip it.
Generation gets you something close; editing gets you the thing you asked for. Being able to hand back an image and describe the change — rather than re-rolling a prompt and hoping — is the difference between a toy and a tool you use twice. Costs land on your own OpenAI key, so the spending is visible where you already watch it.
What it is
A tool server over OpenAI's image generation and editing endpoints, exposing the editing half rather than generation alone.
What you get
- Image generation from a prompt
- Editing an existing image rather than regenerating it
- Advanced prompt control over the request
Requirements
An OpenAI API key, and npx to run it. MIT licensed.
Setup effort
One command plus a key — npm install -g openai-gpt-image-mcp-199bio, then supply credentials
USE CASES
01
Making an image
Prompt to picture, on your own API key.
02
Fixing one instead of re-rolling
Edit the image you have.
2 tools
Listed in project docs. Your client may show a different list.
edit-imageBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- npx on PATH
- OPENAI_API_KEY in your environment
Where it runs
All 4 documented clients run the server on your machine.
INSTALLATION
Connect your client
Server setup
TERMINAL
npm install -g openai-gpt-image-mcp-199bioMCP Clients
Claude Desktop, Cursor, Windsurf
JSON
{
"mcpServers": {
"openai-gpt-image": {
"command": "npx",
"args": [
"openai-gpt-image-mcp-199bio"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"openai-gpt-image": {
"command": "npx",
"args": [
"openai-gpt-image-mcp-199bio"
],
"env": {
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>"
}
}
}
}
