Web Scraping & Data Collection MCPサーバー

Puppeteer Real Browser

Provides AI assistants with detection-resistant browser automation capabilities using puppeteer-real-browser.

Webscan

Scans and analyzes web content, extracting information from web pages.

Deep Research

Facilitates comprehensive web research by gathering and structuring data from Tavily's APIs for LLM-powered markdown document creation.

Markdownify UTF-8

Converts various file types and web content into Markdown format with enhanced UTF-8 encoding support.

Mult Fetch

Fetches web content in multiple formats, supporting browser and Node.js environments with intelligent proxy detection.

Data Gouv

Enables interaction with the Data.gouv.fr API, specifically the API Recherche Entreprises, via HTTP+SSE transport.

Docy

Provides LLMs with access to documentation websites by scraping them with crawl4ai, enabling real-time documentation access for AI tools.

Opengov

Enables Claude Desktop to access and analyze open datasets from Socrata-powered government data portals.

Internetdata

Enables TypeScript projects to retrieve and interact with internet data through a structured API.

Scrapi

Scrapes web pages using the ScrAPI service via a Model Context Protocol (MCP) server.

Google Patents

Enables searching Google Patents information via the SerpApi Google Patents API.

OpenRegister

Accesses the German company register via the OpenRegister API to search and retrieve company information.

Wikipedia Image Crawler

Searches and retrieves images from Wikipedia Commons, ensuring adherence to Creative Commons licenses.

Akshare

Converts Akshare data interfaces into a standardized MCP tool format.

Crawl4AI

Enables AI assistants to access web scraping, crawling, and deep research capabilities via the Model Context Protocol.

Cloudflare Browser Rendering

Extracts web content using Cloudflare Browser Rendering for use in LLM context.

Local Web Search

Enables web searches and content extraction from web pages through the Model Context Protocol.

DataForSEO

Connects to the DataForSEO API via Model Context Protocol to retrieve SEO and marketing data.

SearXNG Enhanced

Enhances SearXNG with category-aware web search, website scraping, and date/time retrieval.

Fetch

Retrieves and extracts web content, converting HTML to markdown for easier consumption by LLMs.