ocr
Extract text from image files or URLs using optical character recognition (OCR) with the Florence-2 MCP Server. Process images to retrieve text content efficiently.
Instructions
Process an image file or URL using OCR to extract text.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| src | Yes | A file path or URL to the image file that needs to be processed. |
Input Schema (JSON Schema)
{
"properties": {
"src": {
"anyOf": [
{
"format": "path",
"type": "string"
},
{
"type": "string"
}
],
"description": "A file path or URL to the image file that needs to be processed.",
"title": "Src"
}
},
"required": [
"src"
],
"title": "ocrArguments",
"type": "object"
}