Web Scraping & Data Collection MCP Servers

Jina AI Reader

28

Extracts and formats web content using the Jina AI Reader API for seamless integration with Large Language Models.

Unstructured API

27

Provides an MCP server implementation for interacting with the Unstructured API, offering tools to manage data sources, destinations, and workflows.

SEC Edgar

27

Connects AI models to SEC EDGAR filings through an open-source MCP server, enabling financial research and insights.

KOSPI/KOSDAQ Stock Data

27

Provides KOSPI/KOSDAQ stock data, including OHLCV, market capitalization, fundamental data, and trading volume.

Tiktok

27

Enables searching and retrieving trending TikTok videos and metadata using hashtags.

Oxylabs

27

Enables AI assistants to access and scrape web data using Oxylabs' web scraping technology.

LinkedIn Browser

26

Automates LinkedIn interactions and extracts data through browser automation, respecting terms of service and rate limits.

ZoomEye

26

Queries ZoomEye for network asset information based on dorks and other search parameters.

Markdown Downloader

25

Downloads webpages as Markdown files for easy access and integration with AI tools.

Youtube Data

25

Enables AI language models to interact with and analyze YouTube content through a standardized Model Context Protocol (MCP) interface.

Coin API

25

Provides access to CoinMarketCap's cryptocurrency data for AI-powered applications.

ScrapeGraph

24

Enables language models to leverage AI-powered web scraping capabilities with enterprise-grade reliability.

Chrome Tools

24

Enables remote control of Chrome tabs through the DevTools Protocol for tasks like executing JavaScript, capturing screenshots, and monitoring network traffic.

AKShare

24

Provides financial data analysis capabilities, accessing Chinese and global market information via the AKShare library.

Scrapling Fetch

24

Retrieves text and HTML content from bot-protected websites for AI assistant consumption.

Web3 Research

23

Conduct in-depth cryptocurrency research locally using multiple data sources.

Jina AI

23

Provides access to Jina AI's web services through Claude, enabling web page reading, web search, and fact-checking.

Octagon

23

Provides specialized AI agents for investment research of public and private markets, accessible through a simple prompt interface.

PubMed

22

Enables searching and fetching of articles from the PubMed database.

OneSearch

22

Integrates web search and scraping capabilities using Searxng, Firecrawl, and Tavily.