Supported formats Leave feedback
On this page
The MCP server exposes the full GroupDocs.Markdown engine: every format the .NET library can turn into Markdown — 20+ document, spreadsheet, and e-book formats — is available to your AI agent through convert_to_markdown. The canonical matrix lives in the library documentation: supported document formats.
What each family gives you:
- PDF — the most common source, and the one where structure recovery matters: headings, lists, and tables come across rather than a wall of text.
- DOCX / DOC / RTF / ODT — the cleanest conversions, because the structure is already explicit in the source.
- XLSX / XLS / ODS / CSV / TSV — sheets become Markdown tables.
pagesselects worksheets here, not printed pages. - EPUB / MOBI / CHM — e-books and help files, which is how a lot of internal documentation is still archived.
- TXT — normalised into Markdown with front matter if you ask for it.
Scanned documents are the exception. A PDF that is a picture of a page has no text layer, so the conversion produces images rather than prose. There is no OCR step here — check with get_document_info and your own eyes before feeding a scanned archive into an ingestion run.
Was this page helpful?
Any additional feedback you'd like to share with us?
Please tell us how we can improve this page.
Thank you for your feedback!
We value your opinion. Your feedback will help us improve our documentation.
