Skip to main content
Parzo ships a native MCP (Model Context Protocol) server. Once installed, your AI agent can extract invoice data without writing a single line of integration code — just point it at a PDF and ask.

Installation

Install the MCP server globally via npm:

Configuration

Claude Code

Add Parzo to your Claude Code MCP config file:
Replace inv_your_key_here with your Parzo API key. Get one free →

Cursor

Add the following to your Cursor MCP settings:

Available tools

extract_invoice

Extracts structured data from an invoice PDF file. Example prompt:
The agent will call extract_invoice, poll for the result, and return the full JSON — vendor, buyer, line items, financials, and validation flags.

get_job

Retrieves the status and result of an existing extraction job. Example prompt:

Example workflow

Once Parzo is connected, you can use natural language to process invoices:
The agent will automatically call extract_invoice for each file and synthesize the results.

Verify the connection

After adding the config, restart your client and run:
You should see extract_invoice and get_job listed.

Troubleshooting

“Missing X-API-Key header” — Make sure your API key is set correctly in the env block of your config file. “File not found” — Use the absolute path to the PDF. On Windows with WSL, use /mnt/c/Users/... format. Server not showing up — Restart your MCP client after editing the config file.
The MCP server is open source and published on npm as parzo-mcp. Found a bug? Open an issue on GitHub.