PDF Extraction MCP server

Extracts text and performs OCR on PDF files using Python libraries for tasks like document analysis and content indexing.
Back to servers
Provider
xraywu
Release date
Jan 14, 2025
Language
Python
Stats
4 stars

The PDF Extraction MCP server allows you to extract content from PDF files, supporting both standard PDF reading and OCR capabilities. This server is designed to work with Claude and provides a simple way to process PDF documents.

Installation

For Claude Desktop

You'll need to modify your Claude Desktop configuration file to enable the PDF Extraction MCP server.

Configuration Location

  • MacOS: ~/Library/Application\ Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%/Claude/claude_desktop_config.json

Configuration Options

For development or unpublished servers, add the following to your configuration file:

"mcpServers": {
  "pdf_extraction": {
    "command": "uv",
    "args": [
      "--directory",
      "/Users/xraywu/Workspace/pdf_extraction",
      "run",
      "pdf_extraction"
    ]
  }
}

For published servers, use this simpler configuration:

"mcpServers": {
  "pdf_extraction": {
    "command": "uvx",
    "args": [
      "pdf_extraction"
    ]
  }
}

Usage

The PDF Extraction MCP server offers one main tool:

extract-pdf-contents

This tool extracts content from a local PDF file.

Parameters

  • pdf_path (required): String representing the local file path of the PDF file
  • pages (optional): String representing which page numbers to extract. Page numbers are comma-separated, and negative page numbers are supported (e.g., '-1' means the last page)

Examples

To extract the entire PDF:

extract-pdf-contents(pdf_path="/path/to/your/document.pdf")

To extract specific pages:

extract-pdf-contents(pdf_path="/path/to/your/document.pdf", pages="1,3,5")

To extract the first page and the last page:

extract-pdf-contents(pdf_path="/path/to/your/document.pdf", pages="1,-1")

Features

  • Supports standard PDF text extraction
  • Includes OCR capabilities for scanned documents or images in PDFs
  • Handles selective page extraction through the optional pages parameter

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later