▌BestMCPTools.org
BrowserStack MCP logo

BrowserStack MCP

Real-device cross-browser testing wired directly into your AI agent

Browser AutomationPaidClaudeClaude CodeCursorWindsurfGitHub CopilotModerate✓ Verified
Visit Tool152 stars
Own BrowserStack MCP? Boost it to the top.✦ Upgrade to Featured

Maintenance status

Active
Last code update: September 27, 2026License: AGPL-3.0Checked September 28, 2026

How to Install BrowserStack MCP

$npx -y @browserstack/mcp-server

Requires Claude Desktop, Cursor, Windsurf, or another MCP-compatible client.

Setup by client

Claude Desktop (claude_desktop_config.json)

{
  "mcpServers": {
    "browserstack-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@browserstack/mcp-server"
      ]
    }
  }
}

Cursor (~/.cursor/mcp.json)

{
  "mcpServers": {
    "browserstack-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@browserstack/mcp-server"
      ]
    }
  }
}

VS Code (.vscode/mcp.json)

{
  "servers": {
    "browserstack-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@browserstack/mcp-server"
      ]
    }
  }
}

Claude Code (terminal)

claude mcp add browserstack-mcp -- npx -y @browserstack/mcp-server

Add any API keys or environment variables the server's README lists.

About BrowserStack MCP

BrowserStack's MCP server connects the industry-leading cross-browser testing platform to AI coding agents, enabling automated test creation, execution across real devices and browsers, and results analysis through natural language. It integrates BrowserStack's Automate and App Automate products into any MCP-compatible workflow.

BrowserStack MCP is a Browser Automation MCP server designed for QA, growth, ops, and research teams. It enables driving a real browser from an AI assistant by exposing Playwright/Puppeteer sessions as MCP tools. Key capabilities include navigate, click, type, and submit, headless screenshots and pdfs, form-fill and file-upload flows, and structured tool calls that work cleanly inside an LLM context. It integrates with Playwright, Puppeteer, headless Chromium, and Selenium grids, and is best suited for QA, growth, ops, and research teams who need end-to-end testing.

Key Features

  • testing
  • browser-automation
  • qa
  • cross-browser
  • devops

Pricing

Paid: from From $39/month

Pros & Cons

Pros

  • Reaches sites that don't expose APIs
  • Self-healing test flows
  • Strong selectors paired with LLM context

Cons

  • Slower than direct API calls
  • Brittle against aggressive bot protection
  • Per-session state can leak without isolation

Best For

  • End-to-end testing
  • Scraping rendered pages
  • Form-heavy workflows
  • Dashboard data extraction

Our Take on BrowserStack MCP

BrowserStack MCP brings real-device testing into the AI coding loop. You can now ask your AI agent to run your test suite against 3,000+ real devices and get results back in the same conversation.

Frequently Asked Questions

Tags

#Browser Automation#testing#browser-automation#qa#cross-browser#devops