Web Scraping & Data Collection MCP Servers

Boamp

Retrieves public procurement notices from the BOAMP API using the Model Context Protocol.

Wikipedia

Provides a Model Context Protocol interface for querying Wikipedia content.

Web Scraper Toolkit

Converts websites into LLM-ready assets like Markdown, JSON, and PDF, featuring robust anti-bot evasion and an AI-first design for agent integration.

DNSDumpster

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

Data Fetch Server

Securely fetches web content and extracts data from web pages without executing JavaScript within a sandboxed environment.

Article Scraper

Extracts article content, including title, text, author, and date, from web URLs.

Tavily Proxy

Enables AI-powered web searches via Tavily's API with added HTTP/HTTPS proxy support for enhanced LLM capabilities.

FreeCrawl

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

Arxiv Research Server

Facilitates searching, organizing, and summarizing academic papers from arXiv.

Unpaywall

Enables AI clients to interact with the Unpaywall API for searching articles, retrieving metadata, finding open-access links, and extracting text from OA PDFs.

Parquet

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

TradingView

Fetches TradingView chart snapshots efficiently using Playwright for browser automation, enabling fast and secure visualization of market data.

DAO Proposals

Aggregates live governance proposals from major DAOs, enabling real-time tracking and analysis of decentralized decision-making.

WebforAI Text Extractor

Extracts plain text from web pages using the WebforAI library via a Cloudflare Workers-based Model Context Protocol (MCP) server.

TW Stock Agent

Offers a Model Context Protocol server for querying and analyzing Taiwan stock market data.

Browserbase

Enables LLMs to interact with web pages through cloud browser automation, data extraction, and JavaScript execution.

Twolven Puppeteer

Automates browser interactions for LLMs using Playwright, enabling web page navigation, screenshot capture, and JavaScript execution.

Crawl4AI RAG

Provides advanced web crawling and Retrieval-Augmented Generation (RAG) capabilities for AI agents and coding assistants.

Twitter Username Changes

Tracks historical changes of Twitter usernames to identify potentially suspicious activity.

Gemini Grounding

Provides real-time information access using Google Gemini's grounding capabilities for MCP-compatible clients.