pdf-reader-mcp

Overview

PDF Reader MCP is a robust Model Context Protocol server designed to empower AI agents with enterprise-grade PDF processing capabilities. It offers significant performance advantages over traditional sequential processing through automatic parallelization, allowing users to process large PDF documents (50-100+ pages) in seconds rather than minutes. The server maintains a simple, elegant API while providing advanced features like Y-coordinate based content ordering that preserves document layout natural reading flow, making it particularly valuable for AI comprehension tasks.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• read_pdfsources: Array<{path?: string, url?: string, pages?: string | number[]}>, include_full_text?: boolean, include_metadata?: boolean, include_page_count?: boolean, include_images?: boolean

  Extract text, images, and metadata from PDF files with parallel processing

  Try:Extract text from report.pdfTry:Get metadata from all pages of document.pdfTry:Extract images from pages 1-5 of manual.pdf

Comparable tools

Installation

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["@sylphx/pdf-reader-mcp"]
    }
  }
}

code --add-mcp '{"name":"pdf-reader","command":"npx","args":["@sylphx/pdf-reader-mcp"]}'

npm install -g @sylphx/pdf-reader-mcp

FAQ

How is this different from traditional PDF processing?

PDF Reader MCP uses parallel processing to achieve 5-10x faster performance compared to sequential processing. It also provides Y-coordinate based content ordering that preserves natural document layout.

What types of PDF files are supported?

The server supports local files (both absolute and relative paths on Windows/Unix) and HTTP/HTTPS URLs. It can process documents with text, images, and metadata extraction capabilities.

Compare pdf-reader-mcp with