Pdf Reader MCP

🚀 PDF Reader MCP Server

A Model Context Protocol (MCP) server for reading and extracting text content from PDF files, supporting both local files and URLs.

🚀 Quick Start

The PDF Reader MCP Server is a powerful tool that allows you to read and extract text from PDF files. It supports both local files and URLs, and provides a standardized JSON output format.

✨ Features

• Read text content from local PDF files.
• Read text content from PDF URLs.
• Error handling for corrupted or invalid PDFs.
• Volume mounting to access local PDF files.
• Automatic PDF encoding detection.
• Standardized JSON output format.

📦 Installation

1. Clone the repository:

git clone https://github.com/trafflux/pdf-reader-mcp.git
cd pdf-reader-mcp

2. Build the Docker image:

docker build -t mcp/pdf-reader .

💻 Usage Examples

Basic Usage

Run the Server

To run the server with access to local PDF files:

docker run -i --rm -v /path/to/pdfs:/pdfs mcp/pdf-reader

Replace /path/to/pdfs with the actual path to your PDF files.

If you don't need to use local PDF files:

docker run -i --rm mcp/pdf-reader

MCP Configuration

Add the following to your MCP settings configuration:

{
  "mcpServers": {
    "pdf-reader": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-v",
        "/path/to/pdfs:/pdfs",
        "mcp/pdf-reader"
      ],
      "disabled": false,
      "autoApprove": []
    }
  }
}

For the case without using local PDF files:

{
  "mcpServers": {
    "pdf-reader": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "mcp/pdf-reader"],
      "disabled": false,
      "autoApprove": []
    }
  }
}

Advanced Usage

Available Tools

1. read_local_pdf
   • Purpose: Read text content from a local PDF file.
   • Input:

{
  "path": "/pdfs/document.pdf"
}

- Output:

{
  "success": true,
  "data": {
    "text": "Extracted content..."
  }
}

2. read_pdf_url
   • Purpose: Read text content from a specified PDF URL.
   • Input:

{
  "url": "http://example.com/example.pdf"
}

- Output:

{
  "success": true,
  "data": {
    "text": "Extracted content..."
  }
}

📚 Documentation

Error Handling

When an error occurs, the server will return a response in the following JSON format:

{
  "success": false,
  "error": {
    "code": " ErrorCode ",
    "message": " Error message "
  }
}

Here, ErrorCode is a unique error code, and Error message describes the specific cause of the error.

Dependencies

• Python version: 3.8 or higher.
• Required libraries:
  • Flask (for web services).
  • requests (for handling URL requests).

Project Structure

.
├── README.md                # Project documentation
├── requirements.txt        # List of dependencies
├── app.py                  # Main application file
└── config.py               # Configuration file

📄 License

This project is licensed under the Apache License 2.0. Please refer to the LICENSE file for details.

👨‍💻 Author

• Name: Philip Van de Walker
• Email: philip.vandewalker@gmail.com
• GitHub: https://github.com/trafflux

📞 Contact

If you need to contact us, please send an email to philip.vandewalker@gmail.com or visit the GitHub repository: https://github.com/trafflux/pdf-reader-mcp