Pdf Reader MCP Server (@shtse8pdf Reader Mcp)

🚀 PDF Reader MCP Server

This is a PDF Reader MCP (Multi-Model Collaboration Protocol) server designed specifically for AI agents. Through this server, AI agents can securely extract text, metadata, and other relevant information from PDF files via the MCP protocol.

🚀 Quick Start

The PDF Reader MCP Server enables AI agents to securely access PDF content. Below are the installation and startup steps.

📦 Installation

Install using npm

1. Global installation:

   npm install -g pdf-reader-mcp
   

2. Start the service:

   pdf-reader-mcp start
   

Install using Docker

1. Pull the image:

   docker pull sylphlab/pdf-reader-mcp
   

2. Run the container:

   docker run -p 3000:3000 sylphlab/pdf-reader-mcp
   

✨ Features

• Full-text extraction: Extract the complete text content from a PDF file.
• Specific page extraction: Read the content of specified page numbers or page ranges.
• Metadata extraction: Retrieve the metadata of a PDF, such as the author, title, creation date, etc.
• Page count: Return the total number of pages in a PDF file.
• Multi-source processing: Multiple PDF sources (local paths or URLs) can be processed simultaneously in a single request.
• High security: Strictly limit file access permissions within the project root directory to ensure security.

💻 Usage Examples

Basic Usage

{
  "tool": "read_pdf",
  "args": {
    "source": "path/to/file.pdf"
  }
}

Advanced Usage

{
  "status": "success",
  "result": {
    "text": "PDF 文本内容...",
    "metadata": {
      "title": "文档标题",
      "author": "作者名称",
      "creationDate": "2023-10-05"
    },
    " pageCount": 10
  }
}

📚 Documentation

Advantages

• Security: Ensure security by restricting the file access scope.
• Flexibility: Support local paths and URL sources.
• Efficiency: Provide structured JSON output for easy subsequent processing.

Use Cases

• Data extraction: Extract useful information from a large number of PDF files.
• Document analysis: Used in AI-driven content analysis tools.
• Education: Assist in document processing in learning management systems.

Future Plans

1. Documentation improvement: Add more usage examples and detailed explanations.
2. Performance optimization: Further enhance the parsing speed and efficiency.
3. Function expansion: Consider supporting image extraction and annotation parsing.

Support and Contribution

• Issue feedback: Submit bugs or suggestions on GitHub Issues.
• Code contribution: Refer to CONTRIBUTING.md to learn how to contribute.

📄 License

This project is licensed under the MIT License. Please refer to LICENSE for details.