PDF MCP Server — Document Intelligence

PDF operations + AI-powered document extraction. Extract structured data from invoices, receipts, contracts, resumes, W-2s, 1099s, and bank statements.

Features

• AI Document Extraction - Extract structured JSON from documents using GPT-4o
• Auto-detect document type - Automatically identify invoices, receipts, contracts, etc.
• Vision support - Works with scanned PDFs (no text layer)
• Extract text from PDF documents
• Get metadata including title, author, page count
• Fill form fields in interactive PDFs
• Merge multiple PDFs into one document
• Split PDFs into separate files by page ranges
• Create PDFs from HTML with full CSS support
• Render pages to images (PNG/JPEG)

AI Document Extraction

The pdf.ai_extract tool uses GPT-4o to extract structured data from documents.

Supported Document Types

Type	Key Fields Extracted
invoice	invoice_number, dates, vendor/customer, line_items, totals
receipt	merchant, date, items, totals, payment_method
contract	parties, dates, key_terms, signatures
resume	name, contact, experience, education, skills
w2	employer, employee, wages, tax withholdings
form_1099	payer, recipient, amounts, form_type
bank_statement	account, period, balances, transactions
auto	Auto-detect type and extract relevant fields

AI Extract Example

{
  "tool": "pdf.ai_extract",
  "pdfUrl": "https://example.com/invoice.pdf",
  "documentType": "invoice",
  "openaiApiKey": "sk-..."
}

Output:

{
  "status": "ok",
  "document_type": "invoice",
  "extraction": {
    "invoice_number": "INV-2024-001",
    "vendor_name": "Acme Corp",
    "total": 1234.56,
    "line_items": [
      { "description": "Widget A", "quantity": 10, "unit_price": 100.00, "amount": 1000.00 }
    ]
  },
  "confidence": 0.95
}

All Tools

Tool	What it does
pdf.ai_extract	AI-powered structured data extraction
pdf.open	Load PDF from URL or base64
pdf.get_metadata	Get document info (title, author, pages)
pdf.extract_text	Extract all text content
pdf.render_pages	Convert pages to PNG images
pdf.list_form_fields	List all fillable form fields
pdf.fill_form_fields	Fill form fields with values
pdf.flatten_form	Make form fields permanent
pdf.create_from_html	Generate PDF from HTML content
pdf.merge	Combine multiple PDFs
pdf.split	Split PDF by page ranges
pdf.extract_pages	Extract specific pages

Input Examples

Get Metadata

{
  "tool": "pdf.get_metadata",
  "pdfUrl": "https://example.com/document.pdf"
}

Extract Text

{
  "tool": "pdf.extract_text",
  "pdfUrl": "https://example.com/document.pdf",
  "pages": "1,2,3"
}

Create from HTML

{
  "tool": "pdf.create_from_html",
  "html": "<h1>Hello World</h1><p>This is a PDF.</p>"
}

Merge PDFs

{
  "tool": "pdf.merge",
  "urls": ["https://example.com/doc1.pdf", "https://example.com/doc2.pdf"]
}

Pricing

• PDF operations (open, extract, merge, split): Apify compute costs only
• AI extraction: Your OpenAI API costs (~$0.01-0.10 per document)

Limits

Limit	Value
Max file size	50 MB
Max pages	500
AI extraction pages	10 max
Render DPI	150

Use Cases

• Invoice Processing: Extract vendor, amounts, line items automatically
• Resume Parsing: Get structured candidate data from PDFs
• Contract Analysis: Pull key terms, dates, parties
• Tax Document Processing: Extract W-2 and 1099 data
• Form Automation: Fill tax forms, applications programmatically
• Report Generation: Create PDFs from HTML templates

MCP Integration

Works with Claude Desktop, VS Code, and any MCP-compatible agent.

Claude Desktop (claude_desktop_config.json):

{
  "mcpServers": {
    "pdf-tools": {
      "url": "https://mcp.apify.com?actors=YOUR_USERNAME/pdf-mcp-server"
    }
  }
}

Support

For issues or feature requests, open a ticket on the Issues tab.