Overview

Product video
BrowserStack MCP Server
BrowserStack MCP Server transforms modern developer workflows by enabling powerful, real-time interaction between your IDE AI assistants and the full BrowserStack Test Platform.
This MCP Server requires customers to have an active subscription to BrowserStack:
View on AWS Marketplace
Developers install the MCP Server locally to securely connect tools like GitHub Copilot, Claude, or Cursor and instantly, all from a single interface and by using natural language prompts:
- Perform live device/browser tests
- Run and manage test cases
- Trigger automation suites
- Scan for accessibility
- Debug failures
Key Capabilities
- Manual & Automated Web/App Testing: Live real device/browser sessions
- Test Management: Create, update, execute test cases and runs
- Debugging: Fetch and analyze logs, diagnose failures, recommend AI-powered fixes
- Accessibility Scanning: Detect and suggest fixes for A11y violations
- AI Agent-Driven Workflows: Generate and heal test cases, automate diagnostics
Highlights
- Seamless AI-Driven Test Management Orchestrate complete test workflows directly from your IDE or AI tool. Create, execute, debug, and update test cases with natural language in real time
- Instant Live & Automated Testing from Your Workflow Launch real device/browser sessions, run automation suites, and fetch results no dashboards or manual setup required. All actions stay in your local flow, minimizing distractions
- Security & Privacy First Credentials and test data are protected; nothing is stored or shared externally. MCP Server uses a secure, real-time protocol with data isolation across environments, ensuring compliance and peace of mind for enterprise teams
Details
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
Pricing
Vendor refund policy
No refund
Custom pricing options
How can we make this page better?
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
API-Based Agents & Tools
API-Based Agents and Tools integrate through standard web protocols. Your applications can make API calls to access agent capabilities and receive responses.
Additional details
Usage instructions
Getting Started with BrowserStack MCP Server
To get started using the remove MCP server, follow the instructions below:
Available Tools
This MCP server supports the following tools:
Test Management
- createProjectOrFolder — Create TM project/folder
- createTestCase — Add manual test case
- listTestCases — List test cases
- createTestRun — Create test run
- listTestRuns — List test runs
- updateTestRun — Update test run
- addTestResult — Add execution result
- createTestCasesFromFile — Bulk-create from file
Automate / SDK
- setupBrowserStackAutomateTests — Run tests with SDK
- fetchAutomationScreenshots — Fetch Automate screenshots
Observability
- getFailureLogs — Retrieve error logs
App Live
- runAppLiveSession — Start app testing session
Live
- runBrowserLiveSession — Start browser testing session
App Automate
- takeAppScreenshot — Capture quick app screenshot
- runAppTestsOnBrowserStack — Run automated mobile tests
Accessibility
- accessibilityExpert — WCAG/A11y expert Q&A
- startAccessibilityScan — Run accessibility scan
AI Agents
- fetchSelfHealedSelectors — AI self-healed selectors
- createLCASteps — Generate Low Code Automation steps
- uploadProductRequirementFile — Upload PRD/file for test generation
Prerequisites
- Install Node.js and npm
- Create a BrowserStack account: Sign up
- Get your BrowserStack Access Key from Account Settings
Authentication
Replace YOUR_BROWSERSTACK_KEY with your actual BrowserStack key below.
Claude Desktop
Edit the configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%\Claude\claude_desktop_config.json
Add the below code:
{ "mcpServers": { "browserstack": { "command": "npx", "args": ["-y", "@browserstack/mcp-server@latest"], "env": { "BROWSERSTACK_USERNAME": "<username>", "BROWSERSTACK_ACCESS_KEY": "<access_key>" } } } }Cline
Cline stores MCP server configurations in a JSON file that can be modified.
In the Installed tab, click Configure MCP Servers to access the settings file.
Add the following:
{ "mcpServers": { "browserstack": { "command": "npx", "args": ["-y", "@browserstack/mcp-server@latest"], "env": { "BROWSERSTACK_USERNAME": "<username>", "BROWSERSTACK_ACCESS_KEY": "<access_key>" } } } } **Learn More** MCP Docs: <https://github.com/browserstack/mcp-server?tab=readme-ov-file>Resources
Vendor resources
Support
Vendor support
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Customer reviews
BrowserStack: Essential, Reliable Cross-Browser Testing With Massive Real-Device Coverage
The Live Testing feature is incredibly intuitive; I can spin up a real browser session in seconds and debug issues on the spot. The Automate feature integrates seamlessly with our CI/CD pipeline, which means we catch cross-browser issues early before they reach production.
I also really value the speed and reliability of the sessions — minimal lag even when testing on remote devices. The Accessibility Testing and Percy visual testing add-ons are great bonuses that go beyond just cross-browser checks.
Overall, BrowserStack removes the infrastructure headache entirely and lets the team focus on what matters — shipping quality software.
The pricing is probably the biggest concern — it can get quite expensive, especially for larger teams or when you need multiple parallel sessions. For small startups or individual developers, the cost can feel steep compared to the value received at lower tiers.
Occasionally, session stability can be an issue — I've experienced random disconnections or slow load times during live testing sessions, which can be frustrating when you're in the middle of debugging a tricky issue.
The queue times during peak hours for certain devices can also be a bottleneck, particularly for older or more niche device/OS combinations that are in high demand.
Lastly, while the dashboard has improved over time, the onboarding experience for new team members could be smoother — there's a slight learning curve when setting up Automate with complex CI/CD configurations.
These are relatively minor gripes given the overall quality of the platform, but they are areas where BrowserStack could improve to deliver an even better experience.
BrowserStack solves this problem entirely by providing instant access to a cloud-based infrastructure of real devices and browsers. This means we no longer need to invest in physical hardware or worry about keeping devices updated with the latest OS versions.
The biggest benefit has been the reduction in production bugs. By catching cross-browser compatibility issues early in the development cycle — before code reaches production — we've significantly reduced the number of bug reports coming in from end users on specific devices or browsers.
It has also greatly improved team collaboration. Developers, QAs, and even product managers can jump into a live session and visually verify how a feature looks and behaves across different environments, making feedback loops much faster.
From a time perspective, what used to take days of manual device testing can now be done in hours with automated test runs, freeing up the team to focus on building new features rather than firefighting compatibility issues.
In short, BrowserStack has made our QA process faster, more reliable, and far more scalable — directly contributing to a better product experience for our users.