How to split a document and reassemble the pages you want Leave feedback

split extracts the pages you name, each as its own document. That is the detail that shapes every workflow here: three page numbers produce three files, not one file with three pages.

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.

Pull out pages 3, 6, and 8 of report.pdf.

Three single-page documents land in your output folder. Perfect when each page is the deliverable — a signature page, a certificate, one form from a bundle.

To end up with one document containing those pages, extract and then merge:

Extract pages 3, 6 and 8, then merge the three results into one file in that order.

Two tool families, one prompt. The agent chains split into merge — remembering that merge takes at most four inputs per call, so a long range needs rounds.

The same trick, inverted:

This document has 10 pages. Extract all of them except page 4, then merge the rest back together in order.

Ask for the page count first (get_document_info) so the agent enumerates the right list rather than guessing at the length.

Requesting page 12 of a ten-page document fails — correctly, but it wastes a round trip:

How many pages does this have? Then extract the last three.

In spreadsheet formats the page numbers address worksheets, not printed pages. “Split out sheet 2” is pages: "2", and the result is a workbook containing that sheet.

A reassembled document is subject to the same three-page trim as any other merge output. If a rebuilt eight-page range comes back as three, check get_license_status before looking for a bug.