caption_image

caption_image

Generate descriptive captions for images from URLs or local files using AI vision models. Describe key subjects, scenes, and moods in concise language.

Input Schema

Name	Required	Default
`backend`	No
`file_path`	No
`image_url`	No
`local_model_id`	No
`prompt`	No	Write a concise, vivid caption for this image. Describe key subjects, scene, and mood in 1-2 sentences.

Input Schema (JSON Schema)

{
  "properties": {
    "backend": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Backend"
    },
    "file_path": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "File Path"
    },
    "image_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Image Url"
    },
    "local_model_id": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Local Model Id"
    },
    "prompt": {
      "default": "Write a concise, vivid caption for this image. Describe key subjects, scene, and mood in 1-2 sentences.",
      "title": "Prompt",
      "type": "string"
    }
  },
  "title": "caption_imageArguments",
  "type": "object"
}

Computer Vision MCP Server

Input Schema

Input Schema (JSON Schema)

Other Tools from Computer Vision MCP Server

Related Tools

MCP directory API