"Traditional Welsh Dish Cawl" matching MCP servers:

Checks a website's AI readiness: can ChatGPT, Claude, Perplexity, Google AI and 50+ other AI crawlers (GPTBot, ClaudeBot, PerplexityBot) access it? Scores the site, then generates llms.txt, an AI-crawler robots.txt and JSON-LD, and reads LLM Monitor trends, from Claude Desktop, Cursor and other MCP clients.

Enables an LLM to retrieve live weather forecasts for Israeli cities by using Playwright to drive a real browser and scrape data from weather websites without a traditional API.

Crawls Korean stock market data from Naver Finance, providing real-time information on top searched stocks and detailed stock information by stock code.

Enables read-only listing of the cookbooks on an Eat Your Books shelf and searching those books for recipe references by ingredient, dish, or keyword, returning links, authors, page numbers, ingredients, and categories. Connects to an already signed-in local Chrome session for authentication, exposing the same service as the CLI through two read-only tools.

MCP server for Common Crawl CDX that enables backlink discovery, expired domain finding, and competitor gap analysis without requiring API keys.

Enables fetching, crawling, and analyzing web pages with 29 tools for SEO audits, content extraction, and more.

MCP server to crawl WeChat articles, download images, and convert to Markdown, designed for Cursor IDE and AI tools.

Provides tools for automating LinkedIn job post search and management. Job opportunities often appear in LinkedIn posts first, before they're posted on traditional job boards. By monitoring LinkedIn posts, you can discover opportunities earlier and get a competitive advantage in your job search.

Enables AI agents to perform real Google web searches and render web pages for content extraction using a local Chrome browser, with human-in-the-loop CAPTCHA verification, requiring no API keys.

Enables AI agents to search and compare Facebook Marketplace listings, collect listing details and photos, organize research workspaces, evaluate promising items with reusable product guides, and refresh or revisit results while preserving evidence.

A zero-dependency MCP server that fetches any HTTP(S) URL and returns clean content as text, Markdown, raw HTML, or formatted JSON, with robots.txt compliance and SSRF protection.

MCP server for Cloudflare Browser Rendering Crawl API. Fetches and crawls web pages, returning clean Markdown optimized for LLM consumption.

MCP server providing web search, page opening, and text finding tools for DeepSeek Harness, using DuckDuckGo first with Bing fallback and quality scoring.

MCP server for web crawling, searching, and AI-powered content extraction, supporting single-page, batch, and full-site crawling along with text, news, image, book, and video search.

Enables LLMs to crawl websites via Cloudflare's Browser Rendering API, providing tools to start, monitor, cancel crawls, and retrieve structured content with AI extraction.

Enables searching WeChat official account articles through Sogou WeChat search and fetching full article content via MCP, with anti-scraping handling and paginated search support.

Unofficial MCP server wrapping crawl4ai that enables extraction and analysis of content from web pages, PDFs, Office documents, YouTube videos, and more, with AI-powered summarization and Google search integration to reduce token usage while preserving key information.

Provides preflight checks and domain intelligence so agents can skip domains that will refuse them or charge a fee, covering robots.txt, edge refusals, and HTTP 402 paywalls.

Self-hosted web-intelligence server for Hermes Agent and other MCP clients, featuring hybrid HTTP+browser crawling, document parsing, search, structured extraction, and change detection.

Enables an AI agent to read and operate the Chrome or Edge tabs you are already using — titles, URLs, text, HTML, screenshots, clicks, typing, scrolling, and tab management — via a browser extension and native messaging, without restarting the browser, switching profiles, or opening a debug port. It exposes these capabilities as 19 MCP tools, with access limited to explicitly shared tabs and hardened by per-tab, origin-bound grants plus domain allow/deny lists.