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.
Awesome MCP › Browser Automation
jae-jae/g-search-mcp
The project "g-search-mcp" is a powerful Model Context Protocol (MCP) server designed to perform parallel Google searches using multiple keywords simultaneously. It enhances search efficiency by opening multiple tabs within a single browser instance, allowing concurrent searches. The server intelligently handles CAPTCHA challenges by detecting them and enabling a visible browser mode for user verification when necessary. To avoid detection by search engines, it simulates real user browsing behavior, making the automated searches appear more natural. The search results are returned in a structured JSON format, facilitating easy processing and analysis. Users can configure various parameters such as the number of search results to return per query, page loading timeout, locale settings for search results, and debug mode activation. The server uses the Playwright browser automation tool to perform searches, ensuring robust and reliable operation. The project supports quick setup and usage through npx commands, including installing the required Chromium browser for Playwright. It also integrates with Claude Desktop as an MCP server, allowing seamless configuration and use within that environment. Additional features include debug mode for visualizing browser activity during searches, and flexible parameter adjustments to handle special scenarios like slow page loading or changing search regions. The project is open-source under the MIT License and encourages contributions and usage in automated search tasks where parallel processing and CAPTCHA handling are critical. Overall, g-search-mcp is a specialized MCP server that leverages browser automation and user behavior simulation to efficiently perform parallel Google searches with multiple keywords, making it a valuable tool for automated data collection, research, and analysis workflows that require robust search capabilities.
https://github.com/jae-jae/g-search-mcp
Also in 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).
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.
AgentDeskAI/browser-tools-mcp
BrowserTools MCP is a powerful browser monitoring and interaction tool that leverages the Model Context Protocol to enable AI-powered applications to capture and analyze browser data directly within MCP-compatible IDEs.
BrowserMCP/mcp
Browser MCP is an MCP server and Chrome extension that enables AI applications to automate and control your browser locally using your existing browser profile for privacy, speed, and stealth.
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.
agent-infra/sandbox
agent-infra/sandbox is an all-in-one sandbox environment combining Browser, Shell, File, MCP, and VSCode Server in a single Docker container, providing a unified, secure, and agent-ready platform for AI agent development and testing.