pdfco-mcp

pdfdotco/pdfco-mcp

3.3

If you are the rightful owner of pdfco-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

PDF.co MCP Server provides PDF.co API functionality through the Model Context Protocol (MCP), enabling AI assistants to easily perform various PDF processing tasks.

PDF.co MCP Server is a robust solution that integrates PDF.co API capabilities with the Model Context Protocol (MCP), allowing AI-driven applications to seamlessly execute a wide range of PDF processing tasks. This server facilitates the conversion, editing, and analysis of PDF documents, making it an invaluable tool for businesses and developers who require efficient PDF management. With its comprehensive suite of features, PDF.co MCP Server supports the conversion of PDFs to multiple formats, including JSON, CSV, and Excel, as well as the reverse process. It also offers advanced editing capabilities, such as merging, splitting, and annotating PDFs. Additionally, the server provides powerful search and analysis tools, including text search and AI-driven invoice parsing. Security features like password protection and OCR-based searchability enhancements further enhance its utility. The server is designed to be easily configurable and integrates smoothly with various platforms, making it a versatile choice for diverse PDF processing needs.

Features

  • PDF Conversion Tools: Convert PDFs to and from various formats, including JSON, CSV, Excel, and images.
  • PDF Editing & Modification: Merge, split, and annotate PDFs with text, images, and links.
  • PDF Search & Analysis: Search text, detect tables, and extract invoice data using AI.
  • Security & Accessibility: Add or remove password protection and make PDFs searchable via OCR.
  • File Management: Upload files and track job status for asynchronous operations.

Usages

usage with Cursor IDE

{
  "mcpServers": {
    "pdfco": {
      "command": "uvx",
      "args": ["pdfco-mcp"],
      "env": {
        "X_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

usage with Claude Desktop

{
  "mcpServers": {
    "pdfco": {
      "command": "uvx",
      "args": ["pdfco-mcp"],
      "env": {
        "X_API_KEY": "YOUR_API_KEY_HERE"
      }
    }
  }
}

Tools

  1. pdf_to_json

    Convert PDF and scanned images into JSON representation with text, fonts, images, vectors, and formatting preserved.

  2. pdf_merge

    Merge PDF from two or more PDF, DOC, XLS, images, even ZIP with documents and images into a new PDF.

  3. find_text

    Find text in PDF and get coordinates. Supports regular expressions.