Scrapes webpages using Playwright to extract clean Markdown, designed for integration with AI chat prompts.
Sponsored
lilFetch is an MCP (Model Context Protocol) server engineered to efficiently scrape webpages and convert their content into clean Markdown. It leverages `crawl4ai` and Playwright, utilizing a headless Chromium instance to enable robust data extraction from even JavaScript-heavy sites and dynamic web applications where standard `fetch` or `curl` commands are insufficient. Wrapped for easy `npx` use, lilFetch allows users to seamlessly integrate scraped web content directly into AI chat prompts, empowering tasks such as market research summarization, providing rich context for new file creation, and enhancing general conversational AI capabilities.
Key Features
01Enables HTML and/or text scraping of one or more URLs directly within chat prompts.
02Designed for minimal commands and configuration, ensuring easy installation and quick scraping.
030 GitHub stars
04Provides scraped responses to inform follow-up AI queries for tasks like market research summarization or context generation.
05Leverages Playwright and a headless Chromium instance to scrape JS-heavy sites and web apps reliably.
Use Cases
01Gathering comprehensive context from webpages to inform the creation of new files or documents.
02Scraping specific web content or news headlines for summarization in AI chat tools.
03Conducting market research by extracting and analyzing information from multiple URLs through AI prompts.
