extract_text
Pack: ocrspace · Endpoint: https://gateway.pipeworx.io/ocrspace/mcp
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
| Name | Type | Required | Description |
|---|---|---|---|
image_url | string | yes | URL of an image or PDF to run OCR on. |
language | string | no | Language code for OCR (default ‘eng’). Examples: ‘eng’, ‘fre’, ‘ger’, ‘spa’. |
engine | number | no | OCR engine to use: 1, 2, or 3 (default 2). Engine 2 is best for most cases. |
is_table | boolean | no | Set true to improve layout detection for tables/receipts (default false). |
_apiKey | string | no | Optional — your own OCR.space API key for higher limits; omit to use the shared Pipeworx key. |
Example call
curl -X POST https://gateway.pipeworx.io/ocrspace/mcp \
-H 'Content-Type: application/json' \
-d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"extract_text","arguments":{}}}'Connect
Add this to your MCP client config, or use one-click install buttons:
{
"mcpServers": {
"ocrspace": {
"url": "https://gateway.pipeworx.io/ocrspace/mcp"
}
}
}See Getting Started for client-specific install steps.