Web Scraping & Data Collection MCP Servers

CleanShot

Integrate CleanShot X on macOS with AI assistants, enabling control over screenshots and screen recordings using natural language commands.

Parquet

Enables web searches and information extraction from previous searches, designed for Claude Desktop integration.

Bing Searches

Collects, processes, and analyzes Bing search data to extract insights and patterns.

Knowledge Graph Builder

Transforms text and web content into structured knowledge graphs using local AI models, with persistent storage and real-time visualization.

DNSDumpster

Enables AI assistants to perform DNS reconnaissance through natural language requests.

Scrap

Scrape web pages and extract targeted content using CSS selectors through the Model Context Protocol.

Md Webcrawl

Extracts website content and saves it as markdown files, mapping website structure and links.

DeepRe

Generates in-depth research reports on specified topics using the Google Gemini AI API.

Stocknews

Provides real-time stock data, historical information, and related news.

Marginalia

Provides an MCP interface to search the Marginalia Search engine, which focuses on non-commercial content.

Pokemon

Provides standardized access to comprehensive Pokemon data through an MCP server.

Search Analytics

Provides unified access to Google Analytics 4 and Search Console data through a Model Context Protocol (MCP) interface.

Browserai

Enables AI agents and applications to access and extract real-time web data.

Medium Article Accelerator

Fetches and summarizes Medium.com articles by tag for use with LLMs such as Claude Desktop.

Server Fetch Typescript

Retrieves and converts web content into various formats using a Model Context Protocol server.

Web Cat

Enhances AI models with web search and content extraction capabilities through Python-based APIs.

VideoSum

Extracts content from multiple video platforms and generates intelligent knowledge graphs with OCR support.

SearXNG

Enables language models to perform web searches through SearXNG using the Model Context Protocol.

Prediction Market

Aggregates real-time data from various prediction market platforms.

Url Fetch

Enables Claude or any LLM to fetch content from URLs.