Define your fields
Start from the schema above, or describe your own. Add list fields for every repeating row.
Skip building a PDF pipeline from scratch. Define a schema, then create projects, send PDFs and read structured JSON over the API or MCP—from an agent, a script or a backend job. Results also land in a project table where people can review and edit them.
THE PROBLEM PDF2TABLE SOLVES
Use the API or MCP connection to make PDF table extraction part of an automated workflow, with a defined schema and results available for review.
A SCHEMA TO START FROM
Here is a sample “Agent: expense intake” project. Rename, add or remove fields to match your documents—the list field keeps every repeating row together.
Start from the schema above, or describe your own. Add list fields for every repeating row.
Upload files, paste public links, or send them from your AI assistant or code over the API and MCP.
Edit values in the table, open the source PDF for context, and export everything to Excel or read it as JSON.
ALSO BUILT FOR
READY WHEN YOUR PDF IS
Create a workspace, start from the sample schema, and turn your next batch of PDFs into a table you can actually use.
Start extracting