19,306 MCP servers crawled across 12 categories. 164 deterministic detection rules. Evidence chains, not vibes.
Official Integrations
Browse all →W3C WebMCP toolkit for Chrome 146. Expose any website as a structured MCP server for AI agents.
Fetch web pages with SSRF protection. Returns clean, readable markdown from any URL.
Webpage MCP server
Captures visual screenshots of web pages using Puppeteer with support for authenticated workflows, manual login sessions with cookie persistence, and browser session management for monitoring protected applications and automated testing.
Fetch any web page as clean, AI-ready markdown with smart HTTP-to-browser escalation.
MCP server for the Web Resurrect API — resurrect expired domains via AI assistants
Search the web and extract clean, readable text from webpages. Process multiple URLs at once to speed up research with reliable throttling and error handling. Quickly compile sources and summaries for briefs, reports, or competitive analysis.
A small MCP server for fetching web pages in a form that is easier for LLM clients to use
Extract clean markdown from any URL. Removes boilerplate. For RAG pipelines. x402.
A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities.
MCP Server leveraging crawl4ai for web scraping and LLM-based content extraction (Markdown, text snippets, smart extraction). Designed for AI agent integration.
A web scraping service with HTML extraction tools using ScrapingBee API and FastMCP
Web search using free google search (NO API KEYS REQUIRED)
Enable your AI assistants to perform real-time web searches and retrieve the latest information on any topic. Integrate seamlessly with the WebSearch Crawler API for efficient and accurate search results. Enhance your applications with up-to-date knowledge and insights from the web. This is self-hosted service, free You will need to selfhost web api on local or vps. follow [guide here](https://github.com/mnhlt/WebSearch-MCP/blob/main/README.md)
Web search returning structured results — titles, URLs, snippets. x402 micropayment.
一个简单的本地 web search mcp ,可以集群规模化进行对外提供服务。
A simple, locally hosted Web Search MCP server for use with Local LLMs
MCP server providing web search capabilities for LLMs
Enables automated web security testing for XSS and SQL injection vulnerabilities through Playwright-powered browser automation with screenshot capture and comprehensive error handling.
Denoised web search — fetch, clean, and rerank web content for AI agents with strict size budgets.
Discover WebSim projects, creators, and trending content with powerful search and filters. Inspect project details, screenshots, comments, and engagement stats to guide research and curation. Track user profiles and activity to surface influential creators and relevant assets.
Windows-compatible website downloader for efficient web content retrieval and storage, leveraging asynchronous processing and concurrent downloads for tasks like web scraping and content archiving.
Run **full SEO site audits** from ChatGPT and other MCP clients via **Cool Web Tool**. **Tools** - **`site_audit`** — Crawl and score a URL for content quality, technical SEO, Core Web Vitals-style performance signals, and security-related checks. Returns scores (0–100) and prioritized issues with recommendations. - **`aeo_faq_generator`** — Turn a page into **AEO-friendly FAQs** (optional “People also ask” style context when available). **Auth** - **OAuth 2.0** with your Cool Web Tool account (recommended for ChatGPT), or configure an **API access token** where the host supports it. **Good for** - Quick competitive / client site checks in chat - Answer-engine (AEO) content ideas from a single URL [User flow & setup →](https://coolwebtool.com/resources/docs/integrations/chatgpt-mcp/)