Back
Marketplace/BrowserStack

TL;DR

BrowserStack is a Testing MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent full power of BrowserStack's Test Platform for AI tools. Install in 1 minute with mcpizy install browserstack.

🧪

BrowserStack

Verified

Testing

Last updated May 30, 2026 · By MCPizy team

Full power of BrowserStack's Test Platform for AI tools. Cross-browser and device testing.

Install BrowserStack

Via MCPizy CLI (recommended):
mcpizy install browserstack
Or run directly:
npx -y @browserstack/mcp-server
View on GitHub

Works with

Claude Code
Claude Desktop
Cursor
Windsurf
VS Code + Copilot
Any MCP Client

More Testing MCPs

🧪

QA Sphere

Test management system integration for LLMs. Manage test cases, runs, and coverage.

🐛

Debugg AI

Create and run end-to-end tests in remote browsers. Visual testing automation.

📨

MailSandbox

Fast, zero-dependency email testing tool. Safe email sandbox for development.

Alternatives to BrowserStack

If BrowserStack doesn't fit your stack, these Testing MCP servers solve similar problems.

🧪

Cypress

End-to-end testing framework

🔬

Selenium

Web automation via Selenium WebDriver

⚡

Currents

Fix Playwright test failures with AI. Debug flaky tests and analyze test reports.

Key Takeaways

  • BrowserStack exposes an MCP interface for testing workflows in Claude Code, Cursor and Windsurf.
  • No authentication required — works out of the box once installed.
  • Install in 1 command: mcpizy install browserstack — config written to your client automatically.
  • Free and open source (GitHub source linked above) — verified compatible with every MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, VS Code + Copilot).
  • Best use case: automate testing workflows from your AI agent without leaving the editor.

Frequently asked questions

What is the BrowserStack MCP server?

The BrowserStack MCP server is an Testing Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents full power of BrowserStack's Test Platform for AI tools. It exposes BrowserStack's capabilities as tools the AI can call directly from your editor or CLI.

How do I install BrowserStack MCP with Claude Code?

The fastest way is the MCPizy CLI: run `mcpizy install browserstack` 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 @browserstack/mcp-server` and restarting Claude Code.

Is BrowserStack MCP free?

Yes. The BrowserStack MCP server is free and open source (see the GitHub repository linked on this page). You may still need a BrowserStack account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.

Does BrowserStack MCP work with Cursor and Windsurf?

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.

Manage all your MCPs in one place

Monitor usage, track costs, and discover new MCPs.

Get Started Free
What can I do with BrowserStack MCP?

Once installed, your AI agent can full power of BrowserStack's Test Platform for AI tools directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run BrowserStack operations, inspect results, chain BrowserStack with other MCP servers (see our Workflow Recipes), and automate repetitive testing tasks without leaving your editor.