Tools / image.ocr
Image text recognition
image.ocr
Printed text read from an image, with mean confidence and word count.
MediaLaunch set2 units per callnot cachedMCP: image_ocrv1.0.0
When to use it
Use to read text in a photo, scan or screenshot, for example a receipt, sign or document page. Works on clear printed text; handwriting and heavy stylisation fail.
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: text, mean_confidence, words.
Request
curl -X POST https://agentops.tools/v1/image.ocr \
-H 'content-type: application/json' \
-d '{"url":"https://dummyimage.com/600x200/000/fff&text=Hello+World"}'Over MCP the tool is named image_ocr. Over A2A its skill id is image.ocr. Same input, same envelope.