AI Cursor Scraping Assistant MCP server for AI agents

This tool leverages the Model Context Protocol (MCP) to enhance Cursor AI's capabilities for web scraping tasks. It provides a server that helps analyze websites and automatically generate Scrapy or Camoufox scrapers with minimal effort, making the web scraping process more efficient and accessible.

Installation

To get started with the MCP server for web scraping:

git clone https://github.com/TheWebScrapingClub/AI-Cursor-Scraping-Assistant.git
cd AI-Cursor-Scraping-Assistant

Install the required dependencies:

pip install mcp camoufox scrapy

If you plan to use Camoufox for advanced scraping capabilities, fetch its browser binary:

python -m camoufox fetch

Setting Up the MCP Server

The MCP server provides tools that help Cursor AI analyze web pages and generate XPath selectors. Follow these steps to set it up:

Navigate to the MCPfiles directory:
```
cd MCPfiles
```
Update the CAMOUFOX_FILE_PATH in xpath_server.py to point to your local Camoufox_template.py file.
Start the MCP server:
```
python xpath_server.py
```
In Cursor, connect to the MCP server by configuring it in the settings or using the MCP panel.

Using the Web Scraping Assistant

Creating Scrapers with Cursor AI

Once your MCP server is running, you can use Cursor AI to generate scrapers:

Open the project in Cursor AI
Ensure the MCP server is running

Ask Cursor to create a scraper with a prompt like:

Write an e-commerce PLP scraper for the website gucci.com

Cursor will analyze the website structure, check for anti-bot protection, extract the relevant HTML elements, and generate a complete Scrapy spider.

Available Scraper Types

You can request different types of scrapers based on your needs:

E-commerce PLP (Product Listing Page) - Scrapes product catalogs/category pages
E-commerce PDP (Product Detail Page) - Scrapes detailed product information

For example:

Write an e-commerce PDP scraper for nike.com

Advanced Usage

Camoufox Integration

The project includes Camoufox integration for creating stealth scrapers that can bypass certain anti-bot measures. The MCP tools help you:

Fetch page content using Camoufox
Generate XPath selectors for the desired elements
Create a complete Camoufox scraper based on the template

Working with the MCP Tools

The MCP server provides several useful tools for web scraping:

HTML analysis for identifying key elements
XPath selector generation
Anti-bot protection detection
Content extraction from complex webpage structures

When you send a request through Cursor AI, it communicates with the MCP server to perform these analyses, resulting in more accurate and effective scraper generation.

Troubleshooting

If you encounter issues with the MCP server:

Ensure Python 3.10+ is installed
Verify that all dependencies are correctly installed
Check that the MCP server is running before sending requests through Cursor
Make sure Cursor is properly configured to connect to the MCP server
Verify that the path to the Camoufox template file is correctly set in the configuration

For more information on web scraping techniques and best practices, visit The Web Scraping Club.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "xpath-server" '{"command":"python","args":["MCPfiles/xpath_server.py"]}'

See the official Claude Code MCP documentation for more details.

For 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 > Tools & Integrations and click "New MCP Server".

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

{
    "mcpServers": {
        "xpath-server": {
            "command": "python",
            "args": [
                "MCPfiles/xpath_server.py"
            ]
        }
    }
}

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 explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "xpath-server": {
            "command": "python",
            "args": [
                "MCPfiles/xpath_server.py"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect