How to redact scanned documents and images with an AI agent Leave feedback

A scan is a picture of a document. The words on it are pixels, so pattern matching has nothing to match — redact_text returns zero matches on a scanned page, and zero matches is not the same as nothing sensitive.

Note

The commands and config snippets on this page are for the .NET build of the server — the only platform available today. Installation and client setup: MCP server for .NET. Other platforms will expose the same tools with their own launch command; everything else on this page applies unchanged.

redact_image_area covers a rectangle with a solid colour box, permanently. Coordinates are pixels from the top-left corner of the page.

How big is page 2?

get_document_info returns per-page width and height, which turns “the bottom third” into real numbers. Then:

Cover the bottom third of page 2 with a black box.

For a specific element — a signature, a face, a header — you need its position. Two practical routes: open the page in any viewer and read the coordinates, or render a preview with a tool that can (the GroupDocs.Annotation MCP server can return page images inline) and let a vision-capable model estimate the box.

An area redaction that is 20 pixels short is a redaction that failed, and no response text will tell you. Look at the page. This is the one redaction case where verification cannot be automated by re-running a pattern — the check is your eyes, or a preview the agent can see.

Many PDFs are part text, part scan: a born-digital contract with a scanned signature page. Run both tools:

Redact the email addresses across the whole document, then cover the signature block on page 7, applying the second step to the result of the first.

This server redacts; it does not recognise text in images. That keeps the behaviour predictable — there is no confidence threshold quietly deciding that a blurry name was not a name. If your workflow needs text out of scans, extract it first with a tool built for it, decide what is sensitive, then redact by area.

One redaction per document in evaluation mode means one box. A page needing three covered regions gets one — and looks processed. get_license_status first.