`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

Arguments

{
  "image_url": "https://example.com/receipt.jpg"
}

curl

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":{"image_url":"https://example.com/receipt.jpg"}}}'

TypeScript (@pipeworx/sdk)

import { Pipeworx } from '@pipeworx/sdk';
const pipeworx = new Pipeworx();

const result = await pipeworx.call('extract_text', {
  "image_url": "https://example.com/receipt.jpg"
});

More examples

{
  "image_url": "https://example.com/document.pdf",
  "language": "fre",
  "engine": 2,
  "is_table": true,
  "_apiKey": "your-ocrspace-api-key"
}

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.

extract_text