Parzo Invoice Extraction

Created By
Parzo2 months ago
Extract structured data from any invoice PDF. Returns clean JSON with vendor, buyer, line items, financials and confidence score.
Overview

MCP Server Use Parzo directly inside Claude, Cursor, and any MCP-compatible AI client.

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:

npm install -g parzo-mcp

Configuration

Claude Code

Add Parzo to your Claude Code MCP config file:

{
  "mcpServers": {
    "parzo": {
      "command": "parzo-mcp",
      "env": {
        "PARZO_API_KEY": "inv_your_key_here"
      }
    }
  }
}
{
  "mcpServers": {
    "parzo": {
      "command": "parzo-mcp",
      "env": {
        "PARZO_API_KEY": "inv_your_key_here"
      }
    }
  }
}

Replace inv_your_key_here with your Parzo API key. Get one free →

Cursor

Add the following to your Cursor MCP settings:

{
  "mcpServers": {
    "parzo": {
      "command": "parzo-mcp",
      "env": {
        "PARZO_API_KEY": "inv_your_key_here"
      }
    }
  }
}

Available tools

extract_invoice

Extracts structured data from an invoice PDF file.

ParameterTypeDescription
file_pathstringAbsolute path to the PDF file on your local machine
api_keystringYour Parzo API key (optional if set via env)

Example prompt:

Extract the invoice data from /Users/me/invoices/acme-april.pdf

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.

ParameterTypeDescription
job_idstringThe job ID returned by a previous extraction
api_keystringYour Parzo API key (optional if set via env)

Example prompt:

Get the result of job 3419ae1e-93c3-48a1-95ac-833c390f9916

Example workflow

Once Parzo is connected, you can use natural language to process invoices:

I have 3 invoices in ~/Downloads/invoices/. 
Extract the data from each one and give me a summary 
of the total amount due and due dates.

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:

List the available Parzo tools

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`](https://www.npmjs.com/package/parzo-mcp). Found a bug? Open an issue on GitHub.

Server Config

{
  "mcpServers": {
    "parzo": {
      "command": "npx",
      "args": [
        "parzo-mcp"
      ],
      "env": {
        "PARZO_API_KEY": "inv_your_key_here"
      }
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
Parzo
Star
-
Language
-
License
-
Category

Recommend Servers

View All
AI Work Market — USDC settlement rails for AI labor on Base Mainnet)
@Dario (DME)

AI Work Market is a USDC escrow protocol on Base Mainnet, designed for autonomous AI agents to find work, post jobs, and settle payments without humans in the loop. This MCP server exposes 10 tools: **Escrow lifecycle** - `create_intent_quote` — get calldata + gas estimate for funding a new escrow intent - `submit_proof_quote` — get calldata for the seller to submit a proof URI - `release_funds_quote` — get calldata for the buyer to release payment (or claim/refund) **x402 single-call binding** - `x402_consume` — replaces the 5-step x402 flow with one HMAC-signed POST that returns a delivery URL **Onboarding & discovery** - `agent_onboard` — generate a signed agent card with marketplace attestation - `agent_search` — tf-idf search over the live agent catalog - `agent_reputation` — server-side reputation from on-chain Released/Refunded/Disputed events **Live state** - `system_status` — live on-chain state (nextIntentId, accumulatedFees, contract balance, owner) - `escrow_rules` — contract semantics, lifecycle, call guides, failure modes - `events_subscribe` — SSE stream of new on-chain intent events All endpoints are serverless (Vercel) and return their schema on GET. No browser, no wallet UI required for an agent to integrate. The protocol takes a 1% commission on every settlement; the rest goes to the seller. The full AgentCard is at `/.well-known/agent-card.json` (A2A-compatible). The OpenAPI 3.0.3 spec is at `/.well-known/openapi.json` with `components.securitySchemes` (none, hmacX402). `robots.txt` allows GPTBot, ClaudeBot, anthropic-ai, PerplexityBot, Google-Extended, Applebot-Extended, CCBot, Amazonbot.

7 hours ago
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago