AI Cursor Scraping AssistantSAFE
A powerful tool that leverages Cursor AI and MCP (Model Context Protocol) to easily generate web scrapers for various types of websites.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
A powerful tool that leverages Cursor AI and MCP (Model Context Protocol) to easily generate web scrapers for various types of websites. This project helps you quickly analyze websites and generate proper Scrapy or Camoufox scrapers with minimal effort.
Project Overview
This project contains two main components:
- Cursor Rules - A set of rules that teach Cursor AI how to analyze websites and create different types of Scrapy spiders
- MCP Tools - A collection of Model Context Protocol tools that enhance Cursor's capabilities for web scraping tasks
Prerequisites
- Cursor AI installed
- Python 3.10+ installed
- Basic knowledge of web scraping concepts
Installation
Clone this repository to your local machine:
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, you'll need to fetch its browser binary:
python -m camoufox fetch
Setup
Setting Up MCP Server
The MCP server provides tools that help Cursor AI analyze web pages and generate XPath selectors. To start the MCP server:
- Navigate to the MCPfiles directory:
cd MCPfiles
- Update the
CAMOUFOX_FILE_PATHinxpath_server.pyto point to your localCamoufox_template.pyfile.
- 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.
Cursor Rules
The cursor-rules directory contains rules that teach Cursor AI how to analyze websites and create different types of scrapers. These rules are automatically loaded when you open the project in Cursor.
Detailed Cursor Rules Explanation
The cursor-rules directory contains a set of MDC (Markdown Configuration) files that guide Cursor's behavior when cr
69e2a418b89dOBSERVED · 2026-10-08Exposed tools (4)
2 read · 2 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
fetch_page_content | read | global latest_html |
generate_xpaths | write | Write XPATH selectors for the requested fields using the downloaded HTML file. |
strip_css | read | # Read the HTML file |
write_camoufox_scraper | write | print(f |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (0)
No findings outside the package's declared scope.
Gates applied: no_behavioural_pass.
69e2a418b89dfull audit observations/trust-audit/mcp-server/thewebscrapingclub__ai-cursor-scraping-assistant.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-08 | 69e2a418b89d | SAFE | B | 89 | first audit |
Questions
What is the AI Cursor Scraping Assistant MCP server?
A powerful tool that leverages Cursor AI and MCP (Model Context Protocol) to easily generate web scrapers for various types of websites.
What tools does AI Cursor Scraping Assistant expose?
4 in total: 2 read-only, 2 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is AI Cursor Scraping Assistant safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does AI Cursor Scraping Assistant need?
No credential environment variables were found in its source, so it appears to need none.
How does AI Cursor Scraping Assistant run?
It speaks stdio, so it runs as a local process your client starts.
How current is this page?
The grade is for one exact copy of the source (69e2a418b89d), read on 2026-10-08. The repository is watched and re-audited when it changes.