PDF Reader MCP Server

🚀 PDF Reader

A secure, flexible, and efficient tool for reading PDF files, offering various extraction functions and structured output.

🚀 Quick Start

📦 Installation

Install using npm:

npm install @pdf-reader/core

💻 Usage Examples

Basic Usage

import { PDFReader } from '@pdf-reader/core';

async function main() {
    const reader = new PDFReader();
    const text = await reader.extractText('path/to/your.pdf');
    console.log(text);
}

main().catch(console.error);

Feature Overview

• Text Extraction: Extract text content from PDF files.
• Page Parsing: Support extracting text from specific pages or page ranges.
• Metadata Retrieval: Retrieve relevant metadata of PDF files, such as author, title, etc.

Dependencies

• pdfjs-dist: Use the pdf.js library to process and parse PDF files.
• Zod: Used for input validation and type safety.

Contribution Guide

Community contributions are welcome! Please refer to the Contribution Document to learn how to participate in the development.

✨ Features

• 🛡️ Security: Strictly restrict file access permissions to the project root directory.
• 🌐 Flexibility: Support local relative paths and public URLs.
• 🧩 Unified Functionality: A single read_pdf tool can meet various extraction requirements (full text, specific pages, metadata, page count).
• ⚙️ Structured Output: Return prediction data in an easy - to - parse JSON format.
• 🚀 Easy Integration: Designed for seamless use in the MCP environment via npx or Docker containers.
• ✅ Reliability: Use pdfjs-dist for reliable parsing and Zod for input validation.

📈 Performance Advantages

Preliminary benchmark tests on sample PDFs using Vitest show that the tool has high processing efficiency for various operations:

(Higher hz values indicate better performance. Actual results may vary depending on the complexity of the PDF file and the environment.)

For more detailed information, please refer to the Performance Document.

📚 Documentation

For detailed information, please refer to the project documentation:

• Quick Start Guide
• API Reference Documentation
• Design Principles

🔧 Technical Details

Design Concept

The server prioritizes security by restricting the context to ensure secure file access. At the same time, its design focuses on efficiency and simplicity, facilitating integration with AI agent workflows. It relies on a minimal number of dependencies and uses the reliable pdfjs-dist library for PDF parsing.

For the complete Design Concept Document.

Feature Comparison

Compared with other solutions:

• Compared with direct file access: It provides specific parsing functions for PDFs.
• Compared with general file system tools (e.g., pdftotext): It provides a secure and integrated interface through the MCP interface and generates structured output, improving reliability and ease of use.

For the complete Comparison Document.

Future Plans (Roadmap)

• Documentation:
  • Complete all documentation sections (guides, API reference, design, comparison).
  • Resolve TypeDoc issues and generate API documentation.
  • Add more examples and advanced usage.
  • Implement PWA support and optimize for mobile devices.
  • Add sharing buttons and growth metrics to the documentation website.
• Benchmarking:
  • Conduct comprehensive tests using various PDF files (size, complexity).
• Performance Optimization:
  • Optimize existing functions to improve processing speed and efficiency.

📄 License

No license information provided in the original document.

📞 Contact

If you have feedback or questions, please contact the Maintenance Team.

Thank you for using the PDF Reader!