BrowserMCP is a Browser Automation MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent control your local Chrome browser directly. Install in 1 minute with mcpizy install browsermcp.
Browser Automation
Control your local Chrome browser directly
mcpizy install browsermcpnpx -y @anthropic/mcp-browserFetch YouTube subtitles and transcripts
Next-generation platform for AI agents and browser automation. Headless browsing at scale.
Manage GoLogin browser profiles for multi-account automation and anti-detect browsing.
Control Scrapybara cloud browsers for agentic web automation and scraping.
If BrowserMCP doesn't fit your stack, these Browser Automation MCP servers solve similar problems.
The BrowserMCP MCP server is an Browser Automation Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents control your local Chrome browser directly. It exposes BrowserMCP's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install browsermcp` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @anthropic/mcp-browser` and restarting Claude Code.
Yes. The BrowserMCP MCP server is free and open source (see the GitHub repository linked on this page). You may still need a BrowserMCP account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can control your local Chrome browser directly directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run BrowserMCP operations, inspect results, chain BrowserMCP with other MCP servers (see our Workflow Recipes), and automate repetitive browser automation tasks without leaving your editor.