web-scraping-with-mcp

luminati-io/web-scraping-with-mcp

3.3

If you are the rightful owner of web-scraping-with-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.

This guide provides a comprehensive overview of setting up and using an MCP server for web scraping, particularly with Anthropic's Model Context Protocol (MCP) and Bright Data's tools.

Tools

Functions exposed to the LLM to take actions

fetch_page

Fetches the HTML content of a given URL using Playwright and saves it to a temporary file.

extract_info

Parses the saved HTML file to extract details like title, price, rating, and features, returning a structured dictionary.

Prompts

Interactive templates invoked by user choice

No prompts

Resources

Contextual data attached and managed by the client

No resources