Web Scraping & Data Collection MCP 서버

Perplexity

Enables AI assistants to access and utilize the Perplexity API for search and information retrieval.

Education Data

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

News

Enables AI assistants to search articles, get headlines, and browse news sources via the NewsAPI.

Model Context Protocol Servers

Provides a collection of specialized Model Context Protocol (MCP) servers for diverse use cases.

XPath

Executes XPath queries on XML and HTML content, including fetching content from URLs.

Yanyue

Fetches cigarette data from Yanyue (Yanyue.cn) using an MCP server.

Cybersecurity News

Retrieves the latest cybersecurity news from various websites and integrates with Claude Desktop.

Web Cat

Enhances AI models with web search and content extraction capabilities through Python-based APIs.

Google Search

Scrapes Google Search results and provides structured data, including titles, URLs, and snippets.

Browserai

Provides serverless browser access for AI agents and applications, enabling real-time web data retrieval and interaction.

Gres API

Provides a minimalist AI command server for agents and developers to snap pages, grab sites, source docs, and ask questions via a single interface.

Times Newswire

Facilitates interaction with the New York Times Timeswire API using a Multi-Agent Conversation Protocol (MCP) server.

iReader

Extracts content from various online sources, including webpages, YouTube videos, tweets, and PDFs.

Beijing Car Quota Lottery

Enables AI agents to query Beijing car quota lottery results by scraping data from the Beijing Transportation Commission website.

Fetch

Fetches URLs and YouTube video transcripts.

Cps Data

Exposes a local SQLite database and LanceDB vector database containing information on Chicago Public Schools.

Crawl4AI

Wraps the Crawl4AI library with a Model Context Protocol (MCP) server, providing crawling functionality via Python functions.

Deno2 Playwright

Enables LLMs to interact with and automate web pages using Playwright in a Deno 2 environment.

Scrappey

Control a browser through an LLM using Scrappey's web automation and scraping capabilities.

Go SearXNG

Integrates SearXNG metasearch engine with the Model Context Protocol (MCP).