Web Scraping & Data Collection MCP 服务器

Query Table

Scrapes tabular data from websites like Eastmoney, Iwencai, and TDX using Playwright.

Scrapy

Scrapes websites, from basic HTTP requests to dynamic sites requiring JavaScript execution, using TypeScript.

Selenium WebDriver

Enables automated browser interactions through a comprehensive server with advanced detection evasion and multi-browser support.

WoWS Ship Data

Retrieves detailed World of Warships vessel data from the Wargaming.net API, offering comprehensive statistics and comparison capabilities.

Thordata Scraper

Provides one-click access to any website worldwide, delivering AI-ready structured data by bypassing web data barriers.

Chess

Exposes Chess.com player profiles and statistics through a Model Context Protocol (MCP) server.

Dotnet Websearch

Provides AI clients with tools including web search capabilities and random number generation, built on ASP.NET Core.

Gousto

Provides access to Gousto recipes through a Model Context Protocol server for seamless integration with AI conversation agents.

DataXLR8 Enrichment

Enrich contacts and companies with comprehensive data, including person details, company intel, email verification, tech stack, and hiring signals, using a resilient waterfall provider strategy.

WeChat Official Accounts

Enables AI agents to directly access and analyze WeChat Official Account content by crawling articles using a Selenium-based system.

Military Service Workplace

Searches for military service-exempt companies eligible for alternative service types like industrial function personnel and expert research personnel from the Military Manpower Administration.

YouTube Music

Empower AI assistants with comprehensive control over YouTube Music, including playback, history management, playlist creation, and song downloads.

Cloudflare Crawl

Leverages Cloudflare's Browser Rendering API to fetch and process web pages, delivering clean Markdown content optimized for large language models.

Playwright Extended

Enhances Playwright's Model Context Protocol server with automatic cookie consent dismissal, paywall bypass, and advanced visual page reading capabilities for AI agents.

Brave

Enables Codex to programmatically control the Brave browser, facilitating advanced web interactions and data collection.

FanQie Novel

Integrates FanQie Novel's book, chapter, and comment data, making it accessible to Large Language Model clients via the Model Context Protocol.

Weather

Provides global weather, forecast, and air quality data through a free, no-API-key Open-Meteo interface.

Paper Distill

Facilitate academic paper search, organization, and multi-platform distribution for researchers.

UK Business Compliance

Provides comprehensive UK business compliance intelligence by orchestrating queries across seven regulatory registries, delivering structured, actionable insights to MCP-compatible AI clients.

Agent-Commerce-OS

Enables AI agents to autonomously extract and normalize unstructured web data into clean Markdown or JSON formats via a zero-trust, metered-billing API.