ReadPDFx

Provides automated OCR and PDF processing through MCP tools with STDIO transport.

python

0

GitHub Stars

python

Language

5 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": {
    "irev-mcp-readpdfx": {
      "command": "python",
      "args": [
        "d:/AI/MCP/python/ocr_pdf_mcp/mcp_server_stdio.py"
      ],
      "env": {
        "PYTHONPATH": ".",
        "TESSERACT_CMD": "/usr/bin/tesseract",
        "MCP_SERVER_HOST": "localhost",
        "MCP_SERVER_PORT": "8000"
      }
    }
  }
}

ReadPDFx is an MCP server that provides intelligent OCR and PDF processing through the official MCP SDK using STDIO transport. It automatically detects whether a PDF contains digital text or scanned images and applies the appropriate processing method, helping you extract, analyze, and batch-process PDFs efficiently.

How to use

You run ReadPDFx as an MCP server and connect your MCP-enabled client to it. The server uses STDIO transport, so it reads commands from standard input and writes responses to standard output. Use the available tools toSmartly process PDFs, extract text, perform OCR on images, analyze structure, and batch process multiple files. Start the server with your client configuration and invoke tools by name with the required arguments.

In typical workflows, you will start ReadPDFx on your development machine or server, ensure the required dependencies are installed, and point your MCP client to it. Use the provided tool names in your client requests to perform OCR, text extraction, or batch processing on PDFs. The server handles the appropriate processing path automatically based on the content type of each PDF.

How to install

Prerequisites you need before installing ReadPDFx:

Python 3.8+
Tesseract OCR

# Windows
pip install -r requirements.txt

# Install Tesseract (Windows)
choco install tesseract

# macOS
pip install -r requirements.txt
brew install tesseract

# Linux
pip install -r requirements.txt
sudo apt-get install tesseract-ocr

Additional setup and running

Install dependencies, validate the installation, and prepare the server to run via STDIO. After validation, you can connect MCP clients to start using the tools.

pip install -r requirements.txt

# Validate installation
python validate_tools.py

Configure client connections

Configure your MCP client to connect to ReadPDFx using STDIO. The client will launch the Python script that runs the MCP server under STDIO transport.

{
  "mcpServers": {
    "readpdfx": {
      "command": "python",
      "args": ["d:/AI/MCP/python/ocr_pdf_mcp/mcp_server_stdio.py"],
      "env": {}
    }
  }
}

Available tools

process_pdf_smart

Smart PDF processing that automatically detects digital vs scanned content and applies the appropriate processing flow.

extract_pdf_text

Direct text extraction from digital PDFs.

perform_ocr

OCR processing on image files with language specification.

analyze_pdf_structure

Analyze document structure and metadata to understand layout and content.

batch_process_pdfs

Process multiple PDF files in a directory with specified input and output locations.