Web Scraping & Data Collection MCPサーバー

Swiss Knife

Provides a modular collection of utility tools as a Model Context Protocol server, enhancing the capabilities of AI assistants.

Agents

Automates interactions with services and APIs for web browsing, financial data retrieval, and more through AI agents.

Trendwatch

Provides a FastMCP server to automate the collection and analysis of trending YouTube Shorts, enabling integration with AI platforms.

WebSage

Integrates AI models with web scraping features to efficiently interact with websites, crawl pages, and extract structured data.

Pearch.ai

Facilitates people searches through the Pearch.ai API as a FastMCP service.

URL Text Fetcher

Provides URL text fetching, web scraping, and web search capabilities for AI models via the Model Context Protocol.

Tavily Search

Enables search functionality via the Tavily API within the Model Context Protocol framework.

FastDomainCheck

Checks the registration status of multiple domain names in bulk, providing availability and verification method.

Dominican Congress

Provides access to information about the Dominican Congress, including legislative agendas, legislator activity, and new bills.

Alphavantage

Provides an MCP server for accessing stock market data from the Alphavantage API.

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.

Fetch

Retrieves web page content and YouTube video transcripts efficiently.

Travel Agent

Retrieves visa and immigration information for various countries via an MCP server.

Web Tools

Provides web search and intelligent research capabilities through Claude CLI integration for MCP clients.

Weblok

Enables Large Language Models to search and extract full web page content locally using a headless browser, eliminating the need for API keys.

Feedly

Automates Feedly tasks such as retrieving latest entries from categories and marking entries as read based on user-defined criteria.

Session Code

Provides web search capabilities within an MCP server by integrating with the Tavily API.

Crawl4AI

Wraps the Crawl4AI library with a Model Context Protocol (MCP) server, providing crawling functionality via Python functions.

X

Facilitates interaction with the X (Twitter) API, enabling tweet posting, timeline retrieval, and search functionalities through a Model Context Protocol server.

SpiderFoot

Provides a standardized interface for managing SpiderFoot's open-source intelligence scanning and data retrieval capabilities.