browser automation / MCP
Browser MCP is an MCP server paired with a Chrome extension that lets AI clients (VS Code, Claude, Cursor, Windsurf) automate your actual logged-in browser locally.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Same Chrome-extension MCP-server architecture; choose it when you prefer a focused Chrome-only implementation with MIT licensing.
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
MCP-native browser automation with a human-in-the-loop approval step; choose it when you want MCP browser control plus explicit consent gates.
Give your AI agent a real browser — with a human in the loop. Open-source MCP-native browser agent.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Self-hostable visual web-workflow automation server with API/UI; choose it when you need an orchestration platform rather than a local MCP extension bridge.
Automate browser based workflows with AI
Browser automation MCP with stealth/anti-bot hooks; choose it when bypassing anti-bot defenses matters more than using your existing Chrome profile.
The only browser automation that bypasses anti-bot systems. AI writes network hooks, clones UIs pixel-perfect via simple chat.
Rust CLI for browser automation; choose it when your agent can shell out and you don't want to run an MCP server.
Browser automation CLI for AI agents
Turns websites into CLI commands driven by your logged-in browser; choose it when you want site-specific commands rather than generic MCP browser tools.
Make Any Website into CLI & Use your logged-in browser by AI agent.
CLI skill suite for parallel browser sessions and human handoff; choose it for multi-session agent workflows instead of MCP-based control.
Browser automation CLI built for AI agents. Break through anti-bot walls, hand off to humans across platforms when stuck. Parallel multi-task execution, independent multi-session operation, isolated multi-account browsing.
Multi-agent runtime where each AI agent gets an isolated browser/tools with action recording; choose it when building AG-UI agents rather than hooking an MCP client to your own Chrome.
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
Self-hosted JavaScript browser-automation library; choose it when you want an embeddable JS library instead of an MCP dependency.
Open source and self-hostable browser automation library for AI agents
Python framework for building agent-level browser control; choose it when writing your own Python agent instead of connecting an existing MCP client.
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
TypeScript autonomous-browser toolkit; choose it when coding a TS agent with browser capabilities rather than adding MCP to an IDE.
Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.
TypeScript browser-automation agent oriented to Hyperbrowser's cloud infrastructure; choose it when you want that cloud runtime rather than a local MCP bridge.
AI Browser Automation
CLI + extension that shares a real logged-in browser with shell-capable agents; choose it when your agent runs shell commands but doesn't use MCP.
Let AI agents use your real, logged-in browser without interrupting your work. CLI + extension for browser automation across any shell-capable AI agent.
Browser-infrastructure command layer that learns site structures to reduce token spend; choose it when token cost is the main constraint.
The Browser Infra that learns and cuts token spend by upto 90%
Python client for Oxylabs' cloud browser-agent service; choose it when you want managed proxies/infrastructure and don't mind remote browsing.
AI Browser Agent is an advanced Browser AI tool developed by Oxylabs AI Studio that automates real user browsing tasks using natural language instructions.
TypeScript SDK for building browser agents; choose it when you are writing an agent in TypeScript and need programmatic control rather than MCP.
The SDK For Browser Agents
Deployable browser-sandbox API; choose it when you need browser automation infrastructure behind a REST API rather than local MCP control.
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
Minimal Rust CLI that drives a real browser over CDP; choose it for a tiny, fast shell-controllable bridge without MCP overhead.
A tiny, fast Rust CLI that drives a real browser over the Chrome DevTools Protocol — built for coding agents.
Does the same job, but ships as an app. Useful to a person, not swappable into a codebase.
Standalone vision-first browser-agent app; choose it when you want a ready-to-run AI browser agent instead of wiring MCP into your own browser.
Open-source, vision-first browser agent
Standalone browser purpose-built for agent automation and state sharing; choose it when you are willing to switch browser apps instead of adding an extension to Chrome.
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.
These projects were analysed and named mcp among their alternatives. The relationship is not symmetric — how mcp rates them is a separate judgement, made when mcp is analysed in its own right.
calls mcp “If your app consumes MCP and you need browser control over that protocol rather than a Python import.”
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
calls mcp “choose if your app speaks MCP and needs a server endpoint rather than a CLI.”
Browser automation CLI for AI agents
calls mcp “MCP server approach when you already use MCP clients and need browser control externally.”
JavaScript in-page GUI agent. Control web interfaces with natural language.
calls mcp “MCP server that exposes browser control to AI apps; choose it if your agents communicate over MCP and prefer a protocol over a CLI.”
Make Any Website into CLI & Use your logged-in browser by AI agent.
calls mcp “MCP server for browser control; choose if you need a protocol-agnostic MCP integration rather than a full Python platform.”
Automate browser based workflows with AI
calls mcp “Choose when you want to expose browser control to AI assistants via MCP rather than through a web UI.”
🖥️ Run AI Agent in your browser.
calls mcp “Use it when you need MCP-based control of an existing browser instead of adopting a new browser.”
The fastest browser for AI agents to run browser automation, built for sharing your logged-in browser state with your AI agents, like Codex or Claude Code, without disturbing you. Zero cost, zero config.
calls mcp “When you accept an older, unmaintained MCP browser server.”
Chrome MCP Server is a Chrome extension-based Model Context Protocol (MCP) server that exposes your Chrome browser functionality to AI assistants like Claude, enabling complex browser automation, content analysis, and semantic search.
calls mcp “An older MCP browser-control server for local assistants; choose it only if you want a simpler legacy bridge and don't need Steel's managed sessions/proxies.”
🔥 Open Source Browser API for AI Agents & Apps. Steel Browser is a batteries-included browser sandbox that lets you automate the web without worrying about infrastructure.
calls mcp “Use this MCP server for simple browser control, though it's less maintained and narrower.”
Open-source AI coworkers that each get a computer of their own: a browser, files and tools, with every action decided before it happens and recorded after. Bring any AG-UI agent.
calls mcp “Use as a generic MCP server for browser control, though stale; not a drop-in SDK.”
The SDK For Browser Agents
calls mcp “MCP server that lets AI applications control a browser; run it to expose browser actions to MCP clients, not embed in code.”
Let AI agents browse the web. An autonomous toolkit for browser-based AI agents.