Web Scraping & Data Collection MCP Servers

Google Flights Search & Booking

Facilitates comprehensive flight search and booking capabilities through Google Flights and Duffel API, exposing these functions as tools for AI-powered workflows.

MVG Störung

Provides cached access to Munich Public Transport (MVG) disruption data.

CubeCobra

Provides a server to programmatically access and manage CubeCobra data and tools for developers.

Airbnb

Access Airbnb listing search and detailed information programmatically.

Cloudflare Playwright

Enables AI assistants to control a web browser through a Model Control Protocol (MCP) server hosted on Cloudflare Workers.

Playwright

Automates web browser interactions for Large Language Models using structured accessibility data instead of visual data.

WeChat Article Tools

Automates the retrieval, searching, and summarization of WeChat public account articles.

ArXiv LaTeX

Processes arXiv LaTeX sources to enable precise interpretation of mathematical expressions by Large Language Models.

MixSearch

Provides comprehensive web search functionality with multi-engine support, advanced filtering, and full content extraction via both MCP protocol and a REST API.

Documentation Server

Provides a semantic search server for Model Context Protocol documentation using Redis embeddings.

Apify

Connects AI applications and agents to thousands of ready-built tools for real-time web scraping, data extraction, and automation.

PancakeSwap PoolSpy

Tracks and provides real-time data on newly created liquidity pools on PancakeSwap.

arXiv

Provides a programmable interface for LLMs and AI agents to fetch, filter, and summarize the latest arXiv research papers.

DuckDuckGo

Provides AI assistants with real-time web search capabilities through DuckDuckGo.

Tavily

Enables real-time web search, intelligent data extraction, structured website mapping, and systematic web crawling through Tavily's suite of tools, supporting both SSE and STDIO transport protocols.

DataForSEO

Integrates DataForSEO's Research Toolkit API with Claude Desktop, enabling AI-powered SEO research.

Crawl4AI

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

Jina AI

Access Jina AI's Reader, Embeddings, and Reranker APIs, providing a comprehensive suite of tools for web content processing, search, and semantic analysis.

DNSDumpster

Enables AI assistants to perform detailed DNS reconnaissance by querying the DNSDumpster API.

JMA Data

Access real-time and historical weather observation data and forecasts from the Japan Meteorological Agency (JMA).