Extract structured data from invoices and bank statements
The agent converts unstructured PDF invoices and bank statements into structured JSON or Excel data, enabling automated accounting, reconciliation, and financial analysis without manual data entry.
How it works
The agent identifies the source PDF document (via URL or base64) and selects the appropriate tool based on the document type. For invoices, it uses extract_invoice_data to retrieve vendor details, line items, and GST taxes. For bank statements, it uses parse_bank_statement to categorize transactions and summarize payments. Before acting, the agent should verify the user has provided a valid PDF link and confirm the desired output format (JSON for invoices, Excel for statements). It then executes the tool and returns the structured data to the user for further processing or storage.
Prompt
Paste this into an agent that has the servers below connected. Adjust the names and dates to your own.
Please extract the data from this invoice PDF: [URL]. I need the vendor name, total amount, and GST details in JSON format. Also, parse this bank statement: [URL] and give me a summary of transactions.MCP servers it needs
Source
The vendor page this playbook is drawn from, and the passage that supports it.
extract_invoice_data Team Invoice → structured JSON (vendor, line items, GST taxes, totals)MCP Server — Use AllPDFMagic from Claude, Cursor & AI Agents | AllPDFMagic