BrowserStack MCP Server
@mikeysrecipes
About BrowserStack MCP Server
No overview available yet
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"browserstack-mcp-server": {
"command": "npx",
"args": [
"-y",
"@smithery/cli",
"install",
"@browserstack/mcp-server",
"--client",
"claude"
]
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is BrowserStack MCP Server?
BrowserStack MCP Server integrates BrowserStack's Test Platform with AI tools, enabling manual and automated testing on real devices and browsers directly from your preferred AI client.
How to use BrowserStack MCP Server?
Install the package via npx -y @browserstack/mcp-server@latest in your MCP client configuration (VSCode, Cursor, Claude Desktop), set your BrowserStack username and access key as environment variables, then prompt the AI with testing requests like "open my app on an iPhone 15 Pro Max" or "run my test suite on BrowserStack infra".
Key features of BrowserStack MCP Server
- Manual app testing on real mobile devices
- Manual web testing across browsers and OS
- Test locally hosted websites without deployment
- Run automated tests (Playwright, Selenium)
- Debug test failures with Test Observability
- Perform accessibility testing (WCAG, ADA)
Use cases of BrowserStack MCP Server
- Debug mobile app crashes on real devices
- Test websites on specific browser‑OS combinations
- Run Playwright/Selenium test suites on cloud infrastructure
- Analyze and fix CI/CD test failures with smart tagging
- Check website accessibility compliance
FAQ from BrowserStack MCP Server
What credentials are required?
You need your BrowserStack username and access key, available in Account Settings after signing up and purchasing a plan.
Which MCP clients are recommended?
GitHub Copilot or Cursor for automated testing/debugging; Claude Desktop for manual (Live) testing.
Can I test locally hosted websites?
Yes, the server can seamlessly test websites hosted on localhost without needing to deploy to a remote server.
Is the server still in development?
It is under active development and currently supports a subset of the MCP specification; more features are planned.
What are the system requirements?
Node version 18.0 or later (recommended v22.15.0 LTS).
Frequently asked questions
What credentials are required?
You need your BrowserStack username and access key, available in Account Settings after signing up and purchasing a plan.
Which MCP clients are recommended?
GitHub Copilot or Cursor for automated testing/debugging; Claude Desktop for manual (Live) testing.
Can I test locally hosted websites?
Yes, the server can seamlessly test websites hosted on localhost without needing to deploy to a remote server.
Is the server still in development?
It is under active development and currently supports a subset of the MCP specification; more features are planned.
What are the system requirements?
Node version 18.0 or later (recommended v22.15.0 LTS).
Basic information
More Other MCP servers
Reactive Resume
amruthpillaiA one-of-a-kind resume builder that keeps your privacy in mind. Completely secure, customizable, portable, open-source and free forever. Try it out today!
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Nginx UI
0xJackyYet another WebUI for Nginx
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Peekaboo MCP – lightning-fast macOS screenshots for AI agents
steipetePeekaboo is a macOS CLI & optional MCP server that enables AI agents to capture screenshots of applications, or the entire system, with optional visual question answering through local or remote AI models.
Comments