Web Scraping & Data Collection MCPサーバー

Mew

Extends AI assistant capabilities by providing a Model Context Protocol (MCP) server for integrating external tools and data sources.

Workshop

Integrates external APIs into developer environments via custom Model Context Protocol servers.

Websearch OpenAPI

Provides a web search interface via OpenAPI and MCP, utilizing Google and SearXNG for integration with tools like Open-WebUI and Cherry-Studio.

Librarian

Enables large language models to query Wikipedia for information and automatically fact-check factual claims.

Agent

Transforms documentation into intelligent, searchable knowledge bases using advanced vector embeddings and Retrieval-Augmented Generation.

DeFiLlama Airdrops

Extracts, filters, and ranks cryptocurrency airdrop data from DeFiLlama, providing structured insights for decentralized finance opportunities.

Puppeteer

Automates browser interactions, enabling LLMs to interact with web pages, capture screenshots, and execute JavaScript.

Ephor Youtube

Integrates YouTube functionality into Large Language Models (LLMs) via the Model Context Protocol (MCP).

Tavily

Integrates AI assistants with Tavily's advanced web search and data extraction functionalities.

Web Scout

Integrates web search and content extraction capabilities into your MCP environment.

Web Search AI Agent

Searches, analyzes, and recommends developer tools using AI-powered web scraping and a Large Language Model.

Violett

Extends the Model Context Protocol (MCP) TypeScript SDK to provide a robust server with HTTP request capabilities, intelligent content prompts, and dynamic streaming resource support.

Anna's

Efficiently search and download documents from Anna's Archive using a powerful server and command-line interface.

AnyDbApp

Enables AI-powered database operations, file management, and web content scraping via natural language, featuring dynamic schema evolution, semantic search, and Retrieval Augmented Generation (RAG) capabilities with Ollama integration.

Browser Recorder

Records browsing sessions using MCPML and Playwright.

FreeCrawl

Provides a self-hosted Model Context Protocol server for JavaScript-enabled web scraping and versatile document processing.

Local Claude Servers

Extends Claude Desktop with external capabilities while maintaining full control over data and processing using locally-hosted Model Calling Protocol (MCP) servers.

Bibextract

Extracts survey content and bibliography in BibTeX format directly from arXiv papers.

PubMed

Enables programmatic search and retrieval of scientific articles from PubMed via the NCBI Entrez API.

Food

Provides comprehensive search for food products, including pricing and nutritional data, for AI agents.