How to extract document data with AI agents using MCP Leave feedback
On this page
Extraction is the step that turns a folder of documents into something an agent can reason about. Five tools cover the ways data hides in a file.
NoteThe commands and config snippets on this page are for the .NET build of the server, which ships as a Docker image only. 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.
| You ask | Tool |
|---|---|
| “What does it say?” | extract_text |
| “What is in the table?” | extract_tables |
| “Who wrote it, and when?” | extract_metadata |
| “Save the figures” | extract_images |
| “What does the barcode encode?” | extract_barcodes |
| “How long is it, and what format?” | get_document_info |
- Put the documents in the storage folder the container mounts.
- Ask: “What does invoice.pdf say, and what is in its table?”
- The agent calls
extract_textandextract_tablesand reports both. - Everything happens in a local container — no upload.
extract_text reads a text layer. A born-digital PDF has one; a scan does not. On a scanned page the extraction returns little or nothing — which is a correct statement about the file, not a failure.
Check first when you are not sure:
How many pages is this, and does it have extractable text?
get_document_info plus a one-page text extraction answers it in two cheap calls. And on scans, extract_barcodes still works — see Read barcodes from scans.
extract_text truncates very large outputs and marks where it stopped. For a complete read of a long document, extract per page:
Extract the text of this 40-page report page by page and summarize each section.
docker run --rm -i -v $(pwd)/documents:/data \
ghcr.io/groupdocs-parser/parser-net-mcp:latest
Docker only — this product has no dnx channel (why). Per-client config: Register in AI clients, or run the installer.
- Extract tables into structured data — Markdown to read, JSON to compute.
- Read barcodes from scanned documents — where text extraction stops.
- Extract from a folder in bulk — one prompt, many files.
- On-premise architecture — the corpus stays put.
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.
