BrowserMCP Server

Content

BrowserMCP is a browser automation MCP server paired with a Chrome extension. It lets AI applications such as Claude, Cursor, VS Code, and Windsurf automate a connected tab in the user's existing browser profile rather than launching a fresh browser instance.

The project emphasizes local automation, reuse of the user's current browser profile, and workflows where an AI assistant can test web apps or automate repetitive browser tasks.

Source Review

• https://github.com/BrowserMCP/mcp
• https://browsermcp.io
• https://docs.browsermcp.io
• https://docs.browsermcp.io/setup-extension.md
• https://docs.browsermcp.io/setup-server.md
• https://docs.browsermcp.io/start-automating.md

These sources were reviewed on 2026-06-05. Prefer the live docs for current extension installation, server config, supported clients, and troubleshooting.

Features

• Chrome extension plus local MCP server package.
• Setup examples for Claude, Cursor, VS Code, Windsurf, and other MCP clients.
• Connected-tab automation using the user's existing browser profile.
• Navigation, back/forward, wait, keyboard input, click, hover, drag and drop, text entry, accessibility snapshots, screenshots, and console-log tools.
• Local automation designed to reduce network latency.
• Useful for browser task automation and end-to-end testing workflows.

Installation

Install and pin the BrowserMCP extension from the project site, then add the MCP server to your AI application:

{
  "mcpServers": {
    "browsermcp": {
      "command": "npx",
      "args": ["@browsermcp/mcp@latest"]
    }
  }
}

Open the extension, click Connect on the tab you want the agent to control, and then issue browser automation requests through your MCP client.

Use Cases

• Let an AI coding assistant run end-to-end checks against a local web app.
• Automate repetitive browser tasks in a controlled profile.
• Capture screenshots and accessibility snapshots for UI debugging.
• Reproduce user flows that require an existing logged-in browser session.
• Test form filling, navigation, and client-side behavior from an AI editor.

Safety and Privacy

BrowserMCP is convenient because it uses a real browser profile, but that also makes it sensitive. Prefer a dedicated testing profile, keep unrelated accounts closed, and require approval for submissions, payments, account updates, data deletion, or communication with other people.

Treat connected-tab content, screenshots, console output, and form fields as sensitive. They can contain personal data, credentials, customer records, or internal application state.

Duplicate Check

content/mcp/playwright-mcp-server.mdx covers Playwright-driven browser automation, content/mcp/chrome-devtools-mcp-server.mdx covers the official Chrome DevTools server, and content/mcp/chrome-mcp-server.mdx covers the separate hangwin/mcp-chrome extension bridge. This entry covers the BrowserMCP/mcp project and its BrowserMCP extension workflow.