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
cyberchitta/scrapling-fetch-mcp
scrapling-fetch-mcp addresses a specific failure: an assistant asked to read a documentation page receives a bot-protection challenge instead of content. It uses Scrapling, which combines patchright — a stealth-patched browser automation driver — with curl-cffi, an HTTP client that reproduces browser TLS fingerprints, so requests resemble a real browser at both the network and the runtime level. Content is returned as clean HTML or converted markdown, ready for a model to read rather than as a page of protection-challenge markup. The README is explicit about intended scope: it is optimised for low-volume retrieval of documentation and reference material, and is not designed for high-volume scraping or data harvesting — a limit worth respecting both technically, since volume is what triggers escalated blocking, and in terms of what the tool is for. It requires Python 3.10 or newer with uv, is published on PyPI, and is Apache-2.0 licensed. Alongside the MCP server it ships a Claude Code skill, which the README recommends as the easiest path: installed into a project's .claude/skills directory, it makes Claude reach for this fetcher automatically when a URL turns out to be protected, with no explicit instruction from the user. The audience is developers whose agents need to read technical documentation on sites that block ordinary automated requests.
https://github.com/cyberchitta/scrapling-fetch-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.