MCP Business Pdf Field Extractor
Pull fixed fields and line items from invoice, PO and contract PDFs, no AI
- Pricing
- Paid
- Platforms
- CLI, API
- Runs
- Locally
- Version
- 1.0.2
- Listing updated
- 4 days ago
Similar MCP servers
About MCP Business Pdf Field Extractor
MCP Business Pdf Field Extractor is a paid MCP server for files and documents. It runs locally on your machine and is started by your AI client.
The extractor works from labels and column position rather than a language model, so a value with no known label stays null and is listed as missing. Each PDF is read as text, or sent through OCR when a page has no text layer, then classed as an invoice, purchase order or contract.
Invoices and purchase orders return numbers, dates, parties, totals, line items and a check that the amounts add up. Contracts return parties, dates, term, renewal, notice days, governing law and which standard clauses appear. You pass PDF web addresses (up to 1,000, each up to 40 MB) or one uploaded file.
The package is a thin client: all processing happens in an Apify actor from Mamba Labs, so you need an Apify API token. It is MIT licensed.
Install
Run in a terminal
claude mcp add mcp-business-pdf-field-extractor --env APIFY_TOKEN='<APIFY_TOKEN>' -- npx -y @mambalabsdev/mcp-business-pdf-field-extractorAdd to claude_desktop_config.json
{
"mcpServers": {
"mcp-business-pdf-field-extractor": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-business-pdf-field-extractor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}Add to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp-business-pdf-field-extractor": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-business-pdf-field-extractor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp-business-pdf-field-extractor": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-business-pdf-field-extractor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp-business-pdf-field-extractor": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-business-pdf-field-extractor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp-business-pdf-field-extractor": {
"command": "npx",
"args": [
"-y",
"@mambalabsdev/mcp-business-pdf-field-extractor"
],
"env": {
"APIFY_TOKEN": "<APIFY_TOKEN>"
}
}
}
}Using several servers? Build one config file with the MCP config generator.
Configuration
APIFY_TOKENApify API token from https://console.apify.com/account/integrationsRequired
Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- extract_business_pdf_fields
- Extracts fixed fields and line items from PDFs given by URL or upload.
What it does
- Document type detection
- Works out whether each file is an invoice, purchase order or contract.
- Invoice and PO fields
- Returns numbers, dates, parties, totals and line items with an arithmetic check.
- Contract terms
- Extracts parties, term, renewal, notice days and governing law.
- OCR for scans
- Reads pages without a text layer in seven languages.
- Spend cap
- A max_charge_usd input stops the run before a charge passes it.
- Line item rows
- Can emit each line item as its own row for CSV or Clay.
Good for
- Turn supplier invoices into structured rows
- Check totals on purchase orders
- Scan contracts for renewal and notice wording
- Feed document fields into a Clay table
Pricing
Paid
Pay per event on Apify: from $0.01 per document, $0.015 per OCR page
MCP Business Pdf Field Extractor FAQ
Does it use AI?
The README says no; it relies on labels and column position.
What does it cost?
Pay per event on Apify: 0.01 USD per document on the free plan, 0.015 per OCR page and 0.004 per run start.
What do I need?
Node.js 18 or newer and an Apify API token set as APIFY_TOKEN.
Are failed downloads charged?
No. The README says documents with no fields read, failed downloads and refused input are free.
Is MCP Business Pdf Field Extractor free?
No. MCP Business Pdf Field Extractor is a paid product.
How do I add MCP Business Pdf Field Extractor to Claude Code?
Run this command in your terminal: claude mcp add mcp-business-pdf-field-extractor --env APIFY_TOKEN='<APIFY_TOKEN>' -- npx -y @mambalabsdev/mcp-business-pdf-field-extractor
What are the best alternatives to MCP Business Pdf Field Extractor?
The closest alternatives to MCP Business Pdf Field Extractor are Suidasu, Doc Extract MCP, Nutrient MCP, Subpay Invoice Reader and Pdfops MCP.
Where this comes from
- Description: written from the project's README.
- Install steps: from the official MCP Registry entry.