browser-use/browser-use
Open-source browser automation agent for LLMs, usable as a Python library, CLI, hosted cloud service, or MCP server exposing browser-control tools.
Awesome MCP › Browser Automation
mzxrai/mcp-webresearch
The MCP Web Research Server is a Model Context Protocol (MCP) server designed to bring real-time web information into Claude, an AI assistant, to facilitate comprehensive and interactive web research. This project integrates Google search capabilities and webpage content extraction to provide Claude with up-to-date information from the internet. It tracks research sessions by maintaining a list of visited pages, search queries, extracted content, screenshots, and timestamps, enabling a structured and traceable research process. Users can easily set up the server by configuring Claude Desktop to automatically start the MCP server when needed. The server offers several tools including `search_google` for performing Google searches and extracting results, `visit_page` for visiting webpages and extracting their content with optional screenshot capture, and `take_screenshot` for capturing the current page's screenshot. These tools empower Claude to conduct detailed and iterative research on any topic. A notable feature is the `agentic-research` prompt, a guided research prompt that instructs Claude to start with broad searches, prioritize authoritative sources, refine research directions based on findings, and keep the user informed interactively while always citing sources with URLs. This enhances the quality and reliability of the research conducted. The project is in a pre-alpha stage and acknowledges potential bugs due to its AI-generated content nature. It supports macOS and requires Node.js 18 or higher along with Playwright for browser automation. The MCP Web Research Server is licensed under MIT and developed by mzxrai. Overall, this project is a specialized MCP server that extends Claude's capabilities by integrating live web research functionalities, making it a valuable tool for users needing real-time, sourced information during their interactions with Claude.
https://github.com/mzxrai/mcp-webresearch
Also in Browser Automation
unclecode/crawl4ai
Open-source async web crawler and scraper that converts websites into clean, LLM-ready Markdown for RAG pipelines and AI agents, with an official MCP server for AI assistants.
microsoft/playwright-mcp
Playwright MCP is an MCP server that enables LLMs to automate and interact with web browsers using structured accessibility snapshots for efficient and deterministic browser automation.
alibaba/page-agent
Page Agent is an in-page JavaScript GUI agent that enables natural language control of web interfaces, offering easy integration without browser extensions or headless browsers.
Skyvern-AI/skyvern
Skyvern automates browser-based workflows using large language models and computer vision, providing a robust and scalable web automation solution that integrates with the Model Context Protocol (MCP).
browser-use/browser-harness
MCP-compatible harness that lets coding agents drive a user's real, logged-in Chrome browser over the DevTools Protocol, writing new helper scripts as it works.
apify/actors-mcp-server
Apify MCP Server is an MCP protocol server implementation that enables AI assistants to interact with Apify Actors for data extraction, web scraping, and automation tasks through a standardized protocol.
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an MCP server implementation that adds advanced web scraping, crawling, and search capabilities to LLM clients like Cursor and Claude, enabling enhanced data extraction and research functionalities.