FireCrawl MCP Server is a powerful web scraping integration for Claude and other LLMs. It provides JavaScript rendering, batch processing, and search capabilities through a Model Context Protocol (MCP) interface. Now with support for self-hosted instances and advanced features like parallel processing, automatic retries, and content filtering

🔍 Model Context Protocol (MCP) tool for parsing websites using the Jina.ai Reader

Example project demonstrating how to use PDFix SDK WebAssembly build in Node.js. Make PDF Files Accessible, Extract Data from PDF, Convert PDF to HTML, Fill-in PDF Form, Stamp PDF and more...

Simple node server to extract relevant content from website source code using Mozilla's Readability.js

A web-based utility for fetching, categorizing, summarizing and managing global news and articles using the GDELT 2.0 API. Designed for content creators, news aggregators, and researchers, this tool simplifies access to up-to-date articles with an intuitive UI and customizable configurations.

A userscript that adds a button to YouTube video pages for copying the transcript with or without timestamps.

Example project demonstrating how to use PDFix SDK WebAssembly build in Node.js. Make PDF Files Accessible, Extract Data from PDF, Convert PDF to HTML, Fill-in PDF Form, Stamp PDF and more...

Document processing and querying system built with FastAPI and React. Upload documents and interact with their content using natural language queries powered by Gemini API and Unstructured.io

Chrome extension to copy YouTube transcripts with AI-friendly features