How to convert just one section of a document to Markdown Leave feedback

Most conversion requests are not about a whole book. They are about chapter 4, the appendix, or the one worksheet with the figures in it. The pages parameter keeps the work proportional.

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.

Convert pages 40 to 52 of handbook.pdf to Markdown.

pages takes a comma-separated list of 1-based numbers — "40,41,42" and so on; an agent expands a range for you. Omit it and the whole document is converted.

How many pages does handbook.pdf have, and what is its title?

get_document_info answers before you commit to a long conversion, and catches an encrypted file up front rather than as a failure.

For “chapter 4” rather than “pages 40-52”, you need the mapping: convert the table of contents pages first, read it, then ask for the range it names. Two small conversions instead of one enormous one.

In XLSX, XLS, and ODS the numbers select worksheets, not printed pages:

Convert worksheet 2 of the model to Markdown.

That is how you get one table into a document without carrying the other fourteen sheets with it.

• Speed — one chapter is a second; a 400-page manual with images is not.
• Metered cost — under metered licensing you are billed for what you process.
• Signal — a RAG index with the one relevant appendix beats one with the entire back catalogue diluting every query.

Unlicensed, only the first three pages are processed regardless of what you ask for. Requesting pages 40-52 unlicensed gets you pages 1-3, quietly. If the output does not start where you expected, that is the reason — get_license_status.