DReview Directory
Sign inSubmit a tool
Back to directory
PR

PDF Reader MCP

Extract text, metadata, and page content from PDF files.
Last updated July 18, 2026
Content/WritingLocal · stdioTypeScript829
GitHub

Overview

A fast PDF reader MCP server that extracts text content, metadata, and per-page content from local PDF files, letting an agent read and reason over PDF documents directly.

Use cases

Summarize the contents of a long PDF report.
Extract specific data points from a PDF without manual copy-paste.
Answer questions grounded in a PDF's actual page content.

Install

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": [
        "@sylphx/pdf-reader-mcp@3.0.14"
      ]
    }
  }
}

FAQ

It extracts embedded text content; scanned PDFs without a text layer require OCR first, which this server doesn't perform itself.