Web Scraping & Data Collection MCP 服务器

Google Search

Proxies requests to the Google Programmable Search Engine, providing caching, rate-limiting, and metrics.

Playwright

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

Live Weather Alerts

Provides real-time weather alerts and detailed forecasts from the US National Weather Service via a Model Context Protocol (MCP) server.

Event GPT

Provides AI-powered, context-aware event recommendations for Germany through a conversational interface.

Claude Hacker News

Integrates Claude Desktop with Hacker News to enhance information flow and streamline interactions.

Superstore

Extracts orders, product data, and web content from Real Canadian Superstore with direct authentication.

Danbooru Tags

Retrieves comprehensive Danbooru tag information and character statistics.

FPL

Accesses Fantasy Premier League (FPL) data and provides a suite of tools for player, team, and gameweek information.

SEO Audit

Performs comprehensive technical SEO audits with Lighthouse integration, site crawling, and automated report generation.

Beatport Scraper

Extracts comprehensive track metadata, audio preview URLs, and cover artwork from Beatport track URLs.

SciTeX Dataset

Unifies access to neuroscience datasets, enabling discovery and fetching of metadata from major repositories like OpenNeuro, DANDI, and PhysioNet through a single Python API and CLI.

Signal Relay

Connects AI agents to SocioLogic's synthetic persona platform via the Model Context Protocol.

Gousto

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

Stealth Fetch

Fetches and parses web content with browser-grade TLS fingerprint impersonation for resilient web data extraction.

Browser

Automate web browsing actions including navigation, clicking, typing, and capturing screenshots through Playwright.

Cloudflare Crawl

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

Brave

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

Trending Hub

Aggregates trending news and hot topics from over 30 diverse online sources into a unified Model Context Protocol server.

Agricultural Commodity Climate

Provides AI agents with comprehensive agricultural commodity climate risk intelligence, including weather stress, pest emergence, trade concentration, and price shock analysis.

Bite-Size Reader

Summarizes web articles, YouTube videos, and Telegram channel posts using advanced multi-provider scraping and LLM technologies, delivering structured JSON summaries via a Telegram bot and a web interface.