GP PDF Reader

Provides advanced PDF text extraction, search, and metadata capabilities with page-range processing and security protections.

javascript

27

GitHub Stars

javascript

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "gpetraroli-mcp_pdf_reader": {
      "command": "node",
      "args": [
        "/absolute/path/to/mcp_gp_pdf_reader/index.js"
      ]
    }
  }
}

You run an MCP server that provides advanced PDF text extraction, search, and metadata capabilities. It lets you extract text from PDFs, search within them with flexible options, and retrieve comprehensive metadata, all in a non-blocking and secure way. You can target specific page ranges, clean the extracted text, and protect against very large files while maintaining responsive performance.

How to use

You interact with the server through an MCP client to perform tasks such as extracting text, searching for terms, and retrieving metadata from PDF documents. Start a local or remote MCP-enabled server, then issue requests to read text from PDFs, search for specific phrases, or fetch metadata. Use the tools to control page ranges, enable or disable text cleaning, and adjust search options like case sensitivity and whole-word matching. When you initiate a task, you receive structured results that you can save, display, or index in your workflows.

How to install

Prerequisites: Node.js 18.0.0 or higher. Ensure you have enough memory and temporary storage for PDF processing. You may also need npm for package management.

Steps to get the MCP server up and running locally:

Install dependencies for the MCP server setup.
Start the MCP server component that exposes the PDF reading capabilities.

Configuration

{
  "mcpServers": {
    "gp_pdf_reader": {
      "command": "node",
      "args": ["/absolute/path/to/mcp_gp_pdf_reader/index.js"]
    }
  }
}

Notes on usage and capabilities

This MCP server exposes three primary tools for PDF handling: read-pdf for text extraction, search-pdf for querying text with options like case sensitivity and whole-word search, and pdf-metadata for metadata extraction. The server also supports page-range processing, text cleaning, file size protections, and non-blocking async operations to keep your workflows responsive.

Security and reliability notes

The server includes validation and path sanitization to reduce risks from untrusted inputs. It enforces a 50 MB file size limit to guard against excessive resource usage and supports asynchronous processing to prevent blocking operations in your workflow.

Usage examples

Basic text extraction, search, and metadata retrieval can be integrated into your automation pipelines by issuing appropriate MCP requests for read-pdf, search-pdf, or pdf-metadata operations.

Development

Developers should ensure Node.js 18+ is installed, and keep dependencies up to date. Monitor memory usage and adjust processing configurations to balance performance with resource constraints.

Available tools

read-pdf

Extract text from PDF files with customizable options including page ranges, metadata inclusion, and text cleaning.

search-pdf

Search for text within PDFs with options for case sensitivity and whole-word matching, plus configurable search parameters.

pdf-metadata

Extract comprehensive metadata from PDF files such as author, title, subject, creator, production details, and more.