Connect OCR Web Service to Your AI Agent

Extract text from public image or PDF URLs and inspect account page limits before processing. Ask your connected AI assistant to explain the results or carry out the specified operation.

2 tools Custom credential

Connect OCR Web Service Install OOMOL

Try a OCR Web Service Task

Copy a prompt into your agent with the oo Skill installed. Add your page links and source notes before running it.

oo Skill OCR Web Service

Extract and Summarize a Document

Request OCR text and ask AI to organize the extracted content.

/oo OCR Web Service: Extract text from [public PDF or image URL] using languages [languages] and return text, then summarize the extracted content and flag unclear passages.

Check Page Allowance

Read account limits before choosing the pages to process.

/oo OCR Web Service: Read OCR Web Service account information and report remaining pages and subscription limits before I submit a document.

Start Working with OCR Web Service

Install OOMOL

Set up oo CLI and the oo Skill in your agent.
Install OOMOL →
Connect OCR Web Service

Provide your OCR Web Service username and license code.
Connect OCR Web Service →
Give Your Agent a Task

Use /oo with the pages to read, the changes to make, and where to save the result.
Connection Guide →

Choose Your Agent

Codex Claude Code Cursor Hermes

An OCR Web Service account, license code, and available processing quota.
Use a public file URL and specify languages or page ranges when needed. Extracted text should be checked against the source for critical details.

OCR Web Service Tools

OCR Web Service connects supported service operations to your AI assistant. Extract text from public image or PDF URLs and inspect account page limits before processing.

Document OCR

Process public image or PDF files with language, page, zone, and output options.

Account Allowance

Read account page limits, plan, and expiration metadata.

2 tools

Get Account Information

Get OCR Web Service account limits, remaining pages, subscription plan, and expiration metadata.

ocr_web_service.get_account_information

Process Document From Url

Download a public image or PDF URL through the connector SSRF guard, upload it to OCR Web Service, and return extracted text or output file metadata.

ocr_web_service.process_document_from_url

Frequently Asked Questions

What file input should I provide?

Provide a publicly reachable image or PDF URL; the connector downloads and uploads the file for OCR.

Can I process only selected pages?

Yes. Specify a supported page range when processing a PDF.

Can I receive both text and output files?

Use the returnText and outputFormats options to request extracted text and supported output file formats.