PDF Reader

Overview

PDF Reader is a Model Context Protocol (MCP) server that extracts text, images, tables, links, annotations, and metadata from PDF files. It integrates directly with AI assistants and language models, exposing PDF processing capabilities as tools they can invoke seamlessly.

The server runs locally as the Python package pdf-insight-mcp, installed via uvx pdf-insight-mcp. It communicates over stdio and requires no authentication—it works immediately after installation. Version v0.2.1 is published under the MIT license with source code available at Xvvln/pdf-reader-mcp on GitHub.

PDF Reader is listed in the File System category and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, claim your listing to verify ownership and keep information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "pdf_reader": {
      "command": "uvx",
      "args": [
        "pdf-insight-mcp"
      ]
    }
  }
}