extract_text
ActiveTool of mcp-ocrspace
declared in 0.1.0
Extract text from an image or PDF via OCR — pass an image/PDF URL, get the recognized text. Useful for reading screenshots, scanned documents, receipts, signs. Engine 2 is best for most cases.
Parameters schema
{
"type": "object",
"required": [
"image_url"
],
"properties": {
"engine": {
"type": "number",
"description": "OCR engine to use: 1, 2, or 3 (default 2). Engine 2 is best for most cases."
},
"_apiKey": {
"type": "string",
"description": "Optional — your own OCR.space API key for higher limits; omit to use the shared Pipeworx key."
},
"is_table": {
"type": "boolean",
"description": "Set true to improve layout detection for tables/receipts (default false)."
},
"language": {
"type": "string",
"description": "Language code for OCR (default 'eng'). Examples: 'eng', 'fre', 'ger', 'spa'."
},
"image_url": {
"type": "string",
"description": "URL of an image or PDF to run OCR on."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
mcp-ocrspace
https://github.com/pipeworx-io/mcp-ocrspace
2/7 registries