OpenAI Images Edit
openai-images-editRead-only
Edit images by providing a prompt and optional mask to inpaint, outpaint, or composite using OpenAI models, supporting 1 to 16 inputs.
Instructions
Edit images (inpainting, outpainting, compositing) from 1 to 16 inputs using OpenAI gpt-image-1.5 (default) or gpt-image-1. Returns MCP CallToolResult with content[] (ResourceLink or ImageContent based on tool_result param) and structuredContent (OpenAI ImagesResponse format with data[].url, data[].path, or data[].b64_json based on response_format param).
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | Absolute image path, base64 string, or HTTP(S) URL to edit, or an array of such values (1-16 images). | |
| prompt | Yes | A text description of the desired edit. Max 32000 chars. | |
| mask | No | Optional absolute path, base64 string, or HTTP(S) URL for a mask image (png < 4MB, same dimensions as the first image). Fully transparent areas indicate where to edit. | |
| model | No | gpt-image-1.5 | |
| n | No | Number of images to generate (1-10). | |
| quality | No | Quality (high, medium, low). Default: high. | high |
| size | No | Size of the generated images. Default: 1024x1536. | 1024x1536 |
| user | No | Optional user identifier for OpenAI monitoring. | |
| tool_result | No | Controls content[] shape: 'resource_link' (default) emits ResourceLink items, 'image' emits base64 ImageContent blocks. | resource_link |
| response_format | No | Controls structuredContent shape: 'url' (default) emits data[].url, 'path' emits data[].path, 'b64_json' emits data[].b64_json. | url |