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
firecrawl/firecrawl-mcp-server
Firecrawl MCP Server is an official implementation of a Model Context Protocol (MCP) server designed to enhance large language model (LLM) clients such as Cursor and Claude by integrating powerful web scraping, crawling, and search capabilities. This server enables deep research, batch scraping, and content extraction from the web, making it a valuable tool for applications that require real-time or extensive web data retrieval. It supports automatic retries and rate limiting to ensure robust and efficient data collection without overwhelming target websites or APIs. Firecrawl MCP Server can be deployed both in cloud environments and as a self-hosted solution, providing flexibility depending on user needs and infrastructure preferences. It also supports Server-Sent Events (SSE) for streaming data, enhancing real-time interaction capabilities. The server is easy to install and configure, with options to run it via npx, manual installation, or integration into various platforms like Cursor, Windsurf, and VS Code. Configuration involves setting environment variables such as the Firecrawl API key and optional parameters for retry behavior and credit usage monitoring. The project provides detailed instructions for setup and usage, including how to configure it within different LLM clients and development environments. Firecrawl MCP Server is particularly useful for developers and researchers who want to augment their LLMs with web data scraping and search functionalities, enabling more informed and contextually rich responses from AI models. The project is actively maintained and encourages users to experiment with it through playgrounds and integrations with other AI tools. Overall, Firecrawl MCP Server bridges the gap between web data and language models by providing a standardized protocol server that facilitates seamless web content discovery and extraction for enhanced AI applications.
https://github.com/firecrawl/firecrawl-mcp-server
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).
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.
executeautomation/mcp-playwright
executeautomation/mcp-playwright is a Model Context Protocol server that enables AI-driven browser automation and web interactions using Playwright.