Web Scraping & Data Collection MCP 서버

Education Data

Provides access to the Urban Institute's Education Data API, enabling retrieval of detailed and aggregated education data.

mcp2brave

Enables Claude and Langchain to perform web searches using the Brave API via an MCP server.

GoScry

Automates web browser interactions through an API for tasks like navigation, data extraction, and authentication.

Rssmcp

Retrieves RSS feeds and formats entries as text using an MCP server.

Hotpepper Gourmet

Provides an unofficial MCP server for accessing the Recruit Hotpepper Gourmet API.

Google Search

Enables web searches using Google Custom Search API and extracts content from webpages.

eStat

Enables generative AI to interact with the Japanese government's e-Stat API.

Polarsteps

Enables AI models to interact with the Polarsteps API for fetching travel data, trip information, and user profiles.

Fetch

Fetches web content for Large Language Models, bypassing robots.txt restrictions.

URL Text Fetcher

Enables LM Studio to fetch web page text and links directly from URLs.

MOEX

Provides an MCP server interface to selected MOEX Information and Statistical Server (ISS) endpoints.

Firecrawl

Integrates advanced web scraping, crawling, and data extraction capabilities into LLM clients such as Cursor, Claude, and Windsurf.

PDF Reader

Extracts text content from PDF files, supporting both local files and URLs.

FetchV2

Fetches and extracts clean, AI-optimized web content, delivering it in a structured markdown format.

Google Search

Perform comprehensive web searches using Google Custom Search JSON API with advanced content extraction capabilities.

TDNET Disclosure

Provides real-time access to TDNET timely disclosures (適時開示) from the Tokyo Stock Exchange, including earnings, dividends, and M&A announcements.

CNKI

Automates comprehensive literature search, detail retrieval, and navigation within the Chinese National Knowledge Infrastructure (CNKI) platform.

RockAuto

Enables AI assistants to search the RockAuto auto parts catalog through natural conversation.

Wick

Provides AI agents with reliable, browser-grade web access by mimicking real browser TLS fingerprints to bypass anti-bot protections.

ATLAS

Applies the scientific method and Popperian falsifiability to rigorously verify claims from social media, news, and blogs using real academic sources.