Content-extraction Packages

A utility for cataloguing the metadata for a URL

A low-level node.js web page content extractor based on `parse5`.

Model Context Protocol server to work with AgentQL

A powerful web content extractor that converts articles to clean markdown

A tool that generates content files from website routes in multiple formats (text, JSON, markdown)

Elegant and powerful Instagram video downloader for seamless content extraction

Hyperbrowser Model Context Protocol Server

Hyperbrowser Model Context Protocol Server

A powerful web crawler that extracts content from web pages and converts them to clean Markdown format, with support for code blocks and GitHub Flavored Markdown

Tool for indexing and searching local knowledge bases with LLM integration

MCP server for JinaAI reader

MCP server for JinaAI search

MCP server for JinaAI grounding

MCP server for Svelte docs

A tool for extracting structured content from web pages with customizable selectors and crawling options

MCP server for FireCrawl web scraping integration. Supports both cloud and self-hosted instances. Features include web scraping, batch processing, structured data extraction, and LLM-powered content analysis.

curl but in markdown - fetches content from URLs and converts to markdown

Model Context Protocol (MCP) server that integrates AgentQL data extraction capabilities.

Crawl-to-markdown is a powerful TypeScript package designed to search search engines for a given keyword, crawl the resulting websites, and deliver the content in clean, readable Markdown format. Additionally, it can directly crawl specified websites for

Extract article content and metadata from web pages.