BrowserStack MCP
by BrowserStack
Official listing: built and published by BrowserStack. More from BrowserStack
Run manual and automated tests on real devices and browsers, scan for accessibility issues and manage test cases from AI agents via BrowserStack's MCP server, for QA teams.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with BrowserStack MCP connected:
- Manual Testing
Use BrowserStack MCP to open mobile apps and websites: ‹what you need›
- Automated Tests
Use BrowserStack MCP to run Playwright, Selenium, Jest and other automated test suites: ‹what you need›
- Accessibility Scans
Use BrowserStack MCP to scan local or production websites for accessibility issues: ‹what you need›
Connect it over MCP
{
"mcpServers": {
"browserstack-mcp": {
"url": "https://mcp.browserstack.com/mcp"
}
}
}claude mcp add --transport http browserstack-mcp https://mcp.browserstack.com/mcp
npx -y @browserstack/mcp-server@latest
In Grok, ChatGPT and other assistants, add a custom connector with the address https://mcp.browserstack.com/mcp (how, step by step).
It may ask you to sign in to BrowserStack or for a key when you add it; the setup guide says which.
Setup guide: browserstack.com/docs/browserstack-mcp-server/get-started/r…
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- MCP
- Auth
- OAuth 2.0
- Skills
- 5
Skills
Manual Testing
Opens mobile apps and websites on BrowserStack's real devices and browsers for manual testing, including sites on localhost.
Automated Tests
Runs Playwright, Selenium, Jest and other automated test suites on BrowserStack and helps debug and fix failures.
Accessibility Scans
Scans local or production websites for accessibility issues and suggests fixes for WCAG and ADA compliance.
Test Management
Creates projects, folders, test cases and test runs in BrowserStack Test Management and updates test results.
Load Testing
Finds and runs load tests, reads results and AI Insights, compares two runs and checks VU-hour quota before a big run.
