A comprehensive Model Context Protocol (MCP) server that provides advanced PDF text extraction, search, and analysis functionality with customizable options for processing local PDF files.

Installation

NPM Install

npm install

Configuration

Cursor

{
  "mcpServers": {
    "mcp-gp-pdf-reader": {
      "command": "node",
      "args": ["/absolute/path/to/mcp_gp_pdf_reader/index.js"]
    }
  }
}

Available Tools

Tool	Description
read-pdf	Extract text from PDF files with customizable options, including page ranges, metadata inclusion...
search-pdf	Search for specific text in PDF documents with search options for case sensitivity, whole words, and regex...
pdf-metadata	Retrieve comprehensive metadata from PDF files, including author, title, creation date, keywords, and more...

Features

• Text extraction from PDF files with customizable options
• Advanced text search with case sensitivity, whole words, and regex options
• Comprehensive metadata extraction (author, title, creation date, keywords)
• Page-by-page processing and content extraction from specific page ranges
• Text cleaning and normalization capabilities
• File size limit protection (50MB limit)
• Asynchronous processing for non-blocking file operations
• File validation and path sanitization for security

Usage Examples

Extract all text from /documents/report.pdf

Search for 'quarterly results' in /documents/financial-report.pdf

Get metadata from /documents/contract.pdf

Notes

Requires Node.js 18.0.0 or higher. Planned future features include OCR support, image extraction, table detection, form data extraction, password-protected PDF support, and batch processing capabilities.