image.inspect

Format, dimensions, EXIF camera and capture data, and dominant colours of an image.

MediaLaunch set1 unit per callnot cachedMCP: image_inspectv1.0.0

When to use it

Use to learn what an image is: its size, format, camera and date from EXIF, and its main colours. EXIF may contain GPS coordinates when the camera recorded them. Dominant colours are only computed for PNG and JPEG.

Input

Field	Type	Description
`url`	`string (≤ 2048 chars)`	Absolute http or https URL of the file. Use instead of base64.
`base64`	`string (≤ 14000000 chars)`	Base64-encoded file bytes, up to 10 MB once decoded. Use instead of url.

Output

Returns data with: format, width, height, bytes, exif: {make, model, software, date_taken, orientation, latitude, longitude} | null, dominant_colors: [{hex, share}] | null.

Request

curl -X POST https://agentops.tools/v1/image.inspect \
  -H 'content-type: application/json' \
  -d '{"url":"https://www.w3.org/Icons/w3c_home.png"}'

Over MCP the tool is named image_inspect. Over A2A its skill id is image.inspect. Same input, same envelope.

Try it

Input (JSON)

Counts against your rate limit.

Sources

exifr (MIT)