@gdm-pixel/pdf-parser-mcp

🔐 Subscription-Based PDF Parser MCP

PDF parsing and text extraction.

⚠️ Requires Nova-Mind Cloud subscription - Starting at €39/month

💎 Open Source Code + Cloud Services

✅ Code is open - Audit, learn, modify freely
🔐 Usage requires subscription - Backend authentication & infrastructure

👉 View pricing | Plans: €39 / €89 / €149 per month

✨ Features

• 📄 PDF Text Extraction - Extract all text content from PDF files
• 📊 Metadata Extraction - Get PDF metadata (title, author, pages, etc.)
• 📂 Batch Processing - Parse multiple PDFs in a directory
• 🔍 Page Limiting - Extract specific page ranges
• ⚡ Fast Processing - Efficient parsing engine
• 🌐 Cross-platform - Works on Windows, macOS, Linux

📦 Installation

With Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "pdf-parser": {
      "command": "npx",
      "args": ["-y", "@gdm-pixel/pdf-parser-mcp@latest"]
    }
  }
}

Config location:

• Windows: %APPDATA%\Claude\claude_desktop_config.json
• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Linux: ~/.config/Claude/claude_desktop_config.json

🚀 Usage

Extract Text from PDF

Extract text from this PDF: C:\Documents\report.pdf

Returns:

• Full text content
• Page count
• Metadata (if available)

Extract with Page Limit

Extract first 10 pages from C:\Documents\long-document.pdf

Useful for:

• Large documents
• Quick previews
• Specific chapters

Get PDF Metadata

Analyze this PDF file: C:\Documents\report.pdf

Returns:

• Title
• Author
• Creator
• Creation date
• Number of pages
• PDF version

List PDFs in Directory

List all PDF files in C:\Documents\Reports

Returns:

• All PDF files found
• File sizes
• File paths

📋 Available Tools

parse-pdf

Extract text content from a PDF file.

Parameters:

• filePath (required) - Absolute path to PDF file
• options (optional) - Parsing options
  • extractMetadata (boolean) - Extract metadata (default: true)
  • maxPages (number) - Maximum pages to extract

Example:

{
  "filePath": "C:\\Documents\\report.pdf",
  "options": {
    "extractMetadata": true,
    "maxPages": 10
  }
}

analyze-pdf

Get detailed PDF information without extracting text.

Parameters:

• filePath (required) - Absolute path to PDF file

Returns:

• Metadata (title, author, dates)
• Page count
• PDF version
• File size

list-pdf-files

List all PDF files in a directory.

Parameters:

• directory (required) - Directory path to scan

Returns:

• Array of PDF file paths
• File sizes
• File names

🔧 Troubleshooting

File Not Found

Problem: "File not found" or "Cannot read PDF" errors

Solutions:

• Verify file path is absolute (not relative)
• Check file exists at specified location
• Ensure file has .pdf extension
• Verify you have read permissions

Extraction Fails

Problem: PDF opens but text extraction fails

Solutions:

• Check PDF is not password protected
• Verify PDF contains actual text (not scanned images)
• For image-based PDFs, you need OCR (not included)
• Try extracting fewer pages with maxPages

Garbled Text

Problem: Extracted text is unreadable or has weird characters

Solutions:

• PDF may have non-standard encoding
• Try different PDF reader to verify content
• Check if PDF is corrupted
• Some encrypted PDFs may produce garbled output

Performance Issues

Problem: Large PDFs take too long to parse

Solutions:

• Use maxPages option to limit extraction
• Process PDFs in smaller chunks
• Close other applications to free up memory
• Consider splitting large PDFs into smaller files

💡 Use Cases

Document Analysis

Extract and summarize this PDF report: C:\Reports\Q4-2024.pdf

Batch Processing

List all PDFs in C:\Documents then extract text from each

Research & Data Extraction

Extract first 5 pages from C:\Papers\research.pdf and find key findings

Content Migration

Extract all text from old PDFs in C:\Archive for new system

Metadata Inspection

Analyze these PDFs and show their metadata: C:\Downloads\*.pdf

📝 Notes

Supported PDF Types

• ✅ Text-based PDFs (created from Word, LaTeX, etc.)
• ✅ PDFs with embedded fonts
• ✅ Multi-page documents
• ❌ Image-only PDFs (requires OCR)
• ❌ Password-protected PDFs
• ⚠️ Scanned documents (may need OCR)

Performance Tips

• Use maxPages for large documents
• Process PDFs in batches
• Extract metadata first to check page count
• Close other applications for large files

Limitations

• No OCR support (image-based PDFs)
• No password-protected PDF support
• No PDF editing/creation
• Text extraction only (no images)

🔒 Security

This tool:

• ✅ Only reads PDF files (no modifications)
• ✅ Works with local files only
• ✅ No data sent to external services
• ✅ No file system modifications
• ✅ Requires explicit file paths

📄 License

MIT © Charles Annoni

🔗 Links

• NPM Package
• Report Issues
• MCP Documentation

🙏 Credits

Created by Charles Annoni (GDM-Pixel)

Part of the Nova-Mind ecosystem - AI-powered coaching platform.

🆘 Need OCR?

For image-based PDFs or scanned documents, you'll need an OCR solution. Consider:

• Adobe Acrobat Pro (commercial)
• Tesseract OCR (open source)
• Online OCR services
• Dedicated OCR MCP server (coming soon)