How to extract tables from documents into structured data Leave feedback

Tables are where the numbers live: invoice line items, price lists, test results, financial summaries. extract_tables gets them out in the shape you need.

Note

The 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.

Extract the tables from invoice.pdf.

The default format: "markdown" returns real Markdown tables, which render immediately in chat, VS Code, and GitHub. When the point is review — does this look right? — this is the format that gets you there fastest.

Extract the line items as JSON and total the amount column.

format: "json" returns structured rows. Now the agent can sum, compare, filter, and cross-check against another system, rather than reading numbers out of rendered text.

The rule: Markdown when a human reads it next, JSON when code does.

Extract the table on page 4.

Table detection across a long document is unnecessary work when you know where the table is. page restricts it — faster, and under metered licensing cheaper.

For each invoice in the folder: extract the line-items table as JSON, total it, and compare the total against the number in the text. Flag any mismatch.

That is two tools (extract_tables and extract_text) and arithmetic the agent does itself — a reconciliation pass over a folder, without a single upload.

• Scans have no tables to find. No text layer means no table structure; the extraction comes back empty. That is the file, not the tool.
• Complex layouts vary. Merged cells, nested tables, and multi-page tables do not always survive as cleanly as a simple grid. Spot-check one document before trusting a batch of two hundred.
• Verify totals, do not assume them. When the arithmetic matters, have the agent show the rows it summed.