JSPM

@dev.saqibaziz/mcp-pdf-reader

1.1.0
  • ESM via JSPM
  • ES Module Entrypoint
  • Export Map
  • Keywords
  • License
  • Repository URL
  • TypeScript Types
  • README
  • Created
  • Published
  • Downloads 29
  • Score
    100M100P100Q71622F
  • License MIT

MCP server for reading and analyzing PDF files from local paths or URLs - enables AI assistants to work with PDFs

Package Exports

  • @dev.saqibaziz/mcp-pdf-reader
  • @dev.saqibaziz/mcp-pdf-reader/dist/index.js

This package does not declare an exports field, so the exports above have been automatically detected and optimized by JSPM instead. If any package subpath is missing, it is recommended to post an issue to the original package (@dev.saqibaziz/mcp-pdf-reader) to support the "exports" field. If that is not possible, create a JSPM override to customize the exports field for this package.

Readme

MCP PDF Reader Server

A Model Context Protocol (MCP) server that enables AI assistants like Claude, Windsurf, and other MCP-compatible tools to read and analyze PDF files.

Features

  • 📄 Read PDF files from local paths or URLs
  • 🔍 Search for specific terms within PDFs
  • 📊 Get PDF metadata (page count, author, title, etc.)
  • 📖 Read specific pages or page ranges
  • 🌐 Download and analyze PDFs from the web
  • 🤖 Seamless integration with AI assistants via MCP

Installation

Using npm

npm install -g @dev.saqibaziz/mcp-pdf-reader

Using npx (no installation required)

npx @dev.saqibaziz/mcp-pdf-reader

Configuration

For Claude Desktop

Add this to your Claude Desktop configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

For Windsurf

Option 1: Via Plugin Store (Coming Soon)

  • Open Windsurf
  • Click the Plugins icon in Cascade panel
  • Search for "PDF Reader"
  • Click Install

Option 2: Manual Configuration

Edit your MCP configuration file:

macOS: ~/Library/Application Support/Windsurf/User/globalStorage/codeium.codeium/mcp_config.json Windows: %APPDATA%\Windsurf\User\globalStorage\codeium.codeium\mcp_config.json Linux: ~/.config/Windsurf/User/globalStorage/codeium.codeium/mcp_config.json

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

After adding, click the refresh button in the Plugins panel.

For Cline

Add this to your MCP settings file:

{
  "mcpServers": {
    "pdf-reader": {
      "command": "npx",
      "args": ["-y", "@dev.saqibaziz/mcp-pdf-reader"]
    }
  }
}

Available Tools

The server provides the following tools to AI assistants:

read_pdf_pages

Read specific pages from a PDF file.

Parameters:

  • pdf_path (string): Path to the PDF file
  • pages (array): List of page numbers to read

read_pdf_page_range

Read a range of pages from a PDF file.

Parameters:

  • pdf_path (string): Path to the PDF file
  • start_page (number): First page to read (inclusive)
  • end_page (number): Last page to read (inclusive)

search_pdf

Search for terms in a PDF file and return pages containing them.

Parameters:

  • pdf_path (string): Path to the PDF file
  • terms (string or array): Search term(s)

get_pdf_metadata

Get metadata from a PDF file (page count, author, title, etc.).

Parameters:

  • pdf_path (string): Path to the PDF file

Usage Examples

Once configured, you can ask your AI assistant:

Local Files:

  • "Read pages 1-5 from document.pdf"
  • "Search for 'machine learning' in research.pdf"
  • "What's the metadata of report.pdf?"
  • "Read page 10 from presentation.pdf"

URLs:

Development

Prerequisites

  • Node.js >= 18.0.0
  • npm or yarn

Setup

# Clone the repository
git clone https://github.com/Saqib-Aziz007/mcp-pdf-reader.git
cd mcp-pdf-reader

# Install dependencies
npm install

# Build the project
npm run build

# Run in development mode
npm run dev

Scripts

  • npm run build - Compile TypeScript to JavaScript
  • npm run dev - Watch mode for development
  • npm start - Run the compiled server
  • npm run prepare - Pre-install build hook

Technical Details

This MCP server is built with:

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

License

MIT License - see LICENSE file for details

Author

Muhammad Saqib Aziz

Support

If you encounter any issues or have questions:

Acknowledgments

Built with the Model Context Protocol by Anthropic.