Web Scraping & Data Collection MCPサーバー

Tagesschau

Provides access to the latest news articles and details from tagesschau.de via an MCP server.

Newsdata

Retrieves up-to-date news using the newsdata.io API.

KMB Bus

Queries real-time bus information for Hong Kong's KMB and Long Win Bus services.

Datos.gob.es

Enables querying and analyzing Spanish public datasets available on datos.gob.es directly from MCP clients.

Internetdata

Leverages dynamic tools defined as trips to provide an updated MCP server.

Linkd

Implements a Model Context Protocol (MCP) server for interacting with the Linkd platform.

Project Synapse

Showcases Agent Communication Protocol (ACP), Agent-to-Agent (A2A), and Model Context Protocol (MCP) capabilities through a collaborative research swarm.

Open Search

Provides 33 specialized, enterprise-grade search and research tools for Claude Desktop, featuring robust security and comprehensive data access.

Deep Research Gemini

Orchestrates a multi-agent system for deep web research powered by the Gemini large language model.

YouTube Transcript DL

Extracts YouTube video transcripts through a versatile server supporting multiple transport protocols and formats.

Web Search

Empowers LLM agents with free web search capabilities through a self-hosted SearXNG backend, eliminating the need for API keys.

Gobbler

Convert diverse content formats like YouTube videos, documents, web pages, and audio into structured markdown that AI systems can immediately reason about.

Webustler

Extracts clean, LLM-ready markdown content from any URL, automatically bypassing anti-bot protections like Cloudflare.

Playwright

Provides browser automation capabilities to large language models through structured accessibility snapshots.

Dev Browser

Enables local Chrome/Chromium tab automation for OpenCode clients by relaying Chrome DevTools Protocol commands without remote debugging.

Spanish Public Data Radar

Access comprehensive Spanish government open data, including grants, legislation, statistics, and the national open data catalog, via an LLM-friendly interface.

Aluvia

Routes AI agent web traffic through trusted US mobile carrier IPs to prevent blocks, CAPTCHAs, and rate limits.

Visa Jobs

Find visa-friendly jobs by scraping LinkedIn, matching employers to sponsorship data, and identifying visa sponsorship mentions in job descriptions.

Perplexity Web

Automates Perplexity.ai searches for AI assistants using browser automation without requiring an API key.

Axure

Extracts visible text, image links, and generates AI-ready summaries from public Axure share pages, with multi-page crawling and OCR fallback.