db56e8d8ee66a7dc3994d233fa86816ab18e0528source_git · sam-david/openai-images-mcp · current release
Observed 2026-08-30T20:26:52.949Z using mcpSecurity-inventory. Status: succeeded. Negotiated protocol: 2025-06-18.
{
"tools": {
"listChanged": true
}
}| Tool | Category | Annotations | Risk |
|---|---|---|---|
create_variationGenerate variations of an existing image using DALL·E 2 (the only model that supports variations). Results are saved to disk and file paths are returned.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"image": {
"type": "string",
"description": "Absolute path to the source image (PNG, square, <4MB)."
},
"n": {
"description": "Number of variations to generate (default 1).",
"type": "integer",
"minimum": 1,
"maximum": 10
},
"size": {
"description": "Output size. Default 1024x1024.",
"type": "string",
"enum": [
"256x256",
"512x512",
"1024x1024"
]
},
"user": {
"type": "string"
},
"output_dir": {
"type": "string"
},
"filename_prefix": {
"type": "string"
},
"return_image_content": {
"type": "boolean"
}
},
"required": [
"image"
]
} | — | — · — | — |
edit_imageEdit one or more existing images using a text prompt and optional mask. Supports gpt-image-1.5, gpt-image-1, gpt-image-1-mini, and dall-e-2. Results are saved to disk and file paths are returned.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 32000,
"description": "Description of the desired edit."
},
"images": {
"minItems": 1,
"maxItems": 16,
"type": "array",
"items": {
"type": "string"
},
"description": "Absolute paths to input image files (png/jpg/webp). Up to 16 for GPT Image."
},
"mask": {
"description": "Absolute path to a mask image. Transparent pixels indicate areas to edit. Must match the first input image's dimensions.",
"type": "string"
},
"model": {
"description": "Model to use. DALL·E 3 does not support edits. Defaults to env DALLE_DEFAULT_MODEL or gpt-image-1.5.",
"type": "string",
"enum": [
"gpt-image-1.5",
"gpt-image-1",
"gpt-image-1-mini",
"dall-e-2"
]
},
"size": {
"type": "string",
"enum": [
"auto",
"1024x1024",
"1536x1024",
"1024x1536",
"512x512",
"256x256"
]
},
"quality": {
"type": "string",
"enum": [
"auto",
"low",
"medium",
"high",
"standard"
]
},
"n": {
"type": "integer",
"minimum": 1,
"maximum": 10
},
"background": {
"type": "string",
"enum": [
"transparent",
"opaque",
"auto"
]
},
"output_format": {
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
]
},
"output_compression": {
"type": "integer",
"minimum": 0,
"maximum": 100
},
"input_fidelity": {
"description": "GPT Image only. 'high' preserves more of the original image.",
"type": "string",
"enum": [
"high",
"low"
]
},
"user": {
"type": "string"
},
"output_dir": {
"type": "string"
},
"filename_prefix": {
"type": "string"
},
"return_image_content": {
"type": "boolean"
}
},
"required": [
"prompt",
"images"
]
} | — | — · — | — |
generate_imageCreate one or more images from a text prompt using OpenAI's image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini, dall-e-3, dall-e-2). Images are saved to disk and file paths are returned.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"prompt": {
"type": "string",
"minLength": 1,
"maxLength": 32000,
"description": "Text description of the image to generate."
},
"model": {
"description": "Model to use. Defaults to env DALLE_DEFAULT_MODEL or gpt-image-1.5.",
"type": "string",
"enum": [
"gpt-image-1.5",
"gpt-image-1",
"gpt-image-1-mini",
"dall-e-3",
"dall-e-2"
]
},
"size": {
"description": "Image dimensions. Allowed values depend on the model (see list_models).",
"type": "string",
"enum": [
"auto",
"1024x1024",
"1536x1024",
"1024x1536",
"1792x1024",
"1024x1792",
"512x512",
"256x256"
]
},
"quality": {
"description": "GPT Image: auto|low|medium|high. DALL·E 3: standard|hd. DALL·E 2: standard.",
"type": "string",
"enum": [
"auto",
"low",
"medium",
"high",
"standard",
"hd"
]
},
"n": {
"description": "Number of images to generate. DALL·E 3 supports only 1.",
"type": "integer",
"minimum": 1,
"maximum": 10
},
"background": {
"description": "GPT Image only. Use 'transparent' with png/webp for alpha channel output.",
"type": "string",
"enum": [
"transparent",
"opaque",
"auto"
]
},
"output_format": {
"description": "GPT Image only. Output file format.",
"type": "string",
"enum": [
"png",
"jpeg",
"webp"
]
},
"output_compression": {
"description": "GPT Image only. Compression % for jpeg/webp (0-100).",
"type": "integer",
"minimum": 0,
"maximum": 100
},
"moderation": {
"description": "GPT Image only. Content moderation strictness.",
"type": "string",
"enum": [
"auto",
"low"
]
},
"style": {
"description": "DALL·E 3 only. Vivid = hyper-real/dramatic, natural = more muted.",
"type": "string",
"enum": [
"vivid",
"natural"
]
},
"user": {
"description": "End-user identifier for OpenAI abuse monitoring.",
"type": "string"
},
"output_dir": {
"description": "Absolute directory to save generated images. Defaults to $DALLE_OUTPUT_DIR or ~/dalle-mcp-output.",
"type": "string"
},
"filename_prefix": {
"description": "Prefix used when naming saved files (alphanumeric/underscore/dash).",
"type": "string"
},
"return_image_content": {
"description": "If true, return the generated images as MCP image content blocks in addition to saving them to disk. Adds significant tokens. Default: false.",
"type": "boolean"
}
},
"required": [
"prompt"
]
} | — | — · — | — |
list_modelsList supported OpenAI image models with their capabilities (sizes, qualities, edit/variation support, etc.). Use this before calling generate_image or edit_image to check which options a model accepts.Input schema{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {}
} | — | — · — | — |