keywords:content-extraction

firecrawl-mcp

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.

hello_sideguide

published version 1.9.0, 12 hours ago1 dependents licensed under $MIT

37,038

fetcher-mcp

MCP server for fetching web content using Playwright browser

jaeger

published version 0.2.6, 10 days ago0 dependents licensed under $ISC

4,783

hyperbrowser-mcp

Hyperbrowser Model Context Protocol Server

a_harmless_pyro

published version 1.0.25, 6 days ago0 dependents licensed under $ISC

2,857

defuddle

Extract article content and metadata from web pages.

kepano

published version 0.6.2, 3 days ago2 dependents licensed under $MIT

1,556

markdown-crawler

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

gkctou

published version 1.0.18, 10 days ago0 dependents licensed under $MIT

591

agentql-mcp

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

tinyfish-agentql

published version 1.0.0, a month ago0 dependents licensed under $MIT

690

js-harvester

Harvester is a lightweight and highly optimized library for extracting data from the DOM tree. It supports tag texts and their attributes. To extract data, the user needs to describe a template of the DOM branch structure from which the extraction will be

flatline-jack

published version 0.2.12, 4 hours ago0 dependents licensed under $MIT

383

@mcpflow.io/mcp-mcp-svelte-docs

🔍 MCP 服务器，可让您使用内置缓存搜索和访问 Svelte 文档。

mcpflow.io

published version 1.0.2, 17 days ago0 dependents licensed under $MIT License

211

reelflow

Elegant and powerful Instagram video downloader for seamless content extraction

h3dev

published version 5.6.5, a month ago0 dependents licensed under $MIT

236

mcp-jinaai-reader

MCP server for JinaAI reader

spences10

published version 0.0.4, 3 months ago0 dependents licensed under $MIT

83

mcp-web-content-pick

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

kilicmu

published version 0.0.25, a month ago0 dependents licensed under $MIT

75

defuddler

A command-line interface for extracting main content from web pages and articles

scotthyndman

published version 1.0.1, 7 days ago0 dependents licensed under $MIT

83

@udx/mcurl

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

andy.potanin

published version 0.3.1, a month ago0 dependents licensed under $MIT

73

webscraping-ai-mcp

Model Context Protocol server for WebScraping.AI API. Provides LLM-powered web scraping tools with Chromium JavaScript rendering, rotating proxies, and HTML parsing.