Web Scraping & Data Collection MCP Servers

LinkedIn

Automates LinkedIn job applications and feed exploration through an MCP server.

Dataset Viewer

Provides access to browse, filter, analyze, and download datasets hosted on the Hugging Face Hub.

Pdf Extraction

Extracts content from PDF files using a local file path.

Aoai Web Browsing

Automates web browser interactions via Playwright, driven by Azure OpenAI and the Model Context Protocol.

SearXNG

Integrates with SearXNG to provide privacy-focused meta search capabilities.

Weibo

Scrape Weibo user information, feeds, and perform content searches.

YouTube Transcript

Extracts transcripts from YouTube videos, enabling content analysis and processing.

Jina AI Reader

Extracts and formats web content using the Jina AI Reader API for seamless integration with Large Language Models.

Jina AI

Provides access to Jina AI's web services through Claude, enabling web page reading, web search, and fact-checking.

Chrome Extension Bridge

Enables interaction between web pages and a local server by establishing a WebSocket connection, allowing access to browser APIs and DOM elements.

Google Patents

Enables searching Google Patents information via the SerpApi Google Patents API.

AutoGen SSE Stdio

Integrates local and remote tools with AI agents using the Model Context Protocol (MCP) within the AutoGen framework.

CodingBaby Browser

Automates Google Chrome through AI agents via a WebSocket connection to a browser extension.

Web Reader

Enables large language models to effortlessly retrieve and parse web content, converting it into clean Markdown format.

Browserai

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

RSS

Fetches and parses standard RSS/Atom feeds, including specialized support for RSSHub, to deliver structured content to language models and other Model Context Protocol clients.

Telegram

Enables AI models like Claude Desktop to interact with Telegram channels and groups for comprehensive content scraping and analysis.

LangExtract

Enables AI assistants to extract structured information from unstructured text using Google's langextract library through an optimized Model Context Protocol interface.

Kagi Ken

Provides programmatic access to Kagi's search and summarization services using a session token, ideal for integration with AI agents and LLMs.

PageMap

Compresses web page HTML into a structured, actionable map, enabling AI agents to efficiently read and interact with web content at significantly reduced token counts.