Lets AI clients manage and run BrowserStack manual and automated tests, debug failures, and run accessibility scans from plain English prompts.
Also known as browserstack/mcp-server, @browserstack/mcp-server
- Stars
- 153
- Tools
- β
- Downloads, 30 days
- 114,405
- Latest version
- 2.6.8
- Last commit
- Nov 13, 2026
- License
- AGPL-3.0
What is BrowserStack MCP?
BrowserStack lets AI clients manage and run BrowserStack manual and automated tests, debug failures, and run accessibility scans from plain English prompts.
Summary generated from the project's README
About BrowserStack MCP server
Managing and executing software tests through natural language is what this server enables for developers using AI-enabled clients like Cursor, Claude, or VS Code. By connecting to the BrowserStack Test Platform, users can trigger manual or automated tests, perform accessibility scans, and manage test plans without leaving their primary development environment. The server supports various testing frameworks including Playwright, Selenium, and Jest, while also providing capabilities for load testing with tools like k6 or JMeter.
To use this server, you need a BrowserStack account with a username and access key. It can be set up locally or via a remote stateless HTTP connection at mcp.browserstack.com. Once connected, the AI assistant uses core tools to search a catalog of workflows, allowing you to request specific actions like debugging an Android 14 crash or running a website on a specific version of Chrome. The system can even suggest code fixes for failed automated tests, though it requires explicit approval before applying any changes to your files.
What you can do with it
- 1Debug mobile application failuresAsk the AI to investigate why an application crashed on a specific mobile operating system.
- 2Execute automated test suitesCommand your AI assistant to run existing automated tests on the BrowserStack infrastructure.
- 3Perform accessibility compliance scansIdentify and fix accessibility issues on local or production websites using automated scans.
- 4Manage test organizationUse natural language to create projects, folders, and specific test cases within a management system.
- 5Analyze load testing performanceRequest detailed metrics and comparisons from recent load testing runs.
Written from the project's README. Every use case is checked against a quote from it.
How to install BrowserStack MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall BrowserStack MCP in Claude Code
$ claude mcp add --env 'BROWSERSTACK_ACCESS_KEY=<YOUR_BROWSERSTACK_ACCESS_KEY>' --env 'BROWSERSTACK_USERNAME=<BROWSERSTACK_USERNAME>' mcp-server -- npx -y @browserstack/mcp-serverInstall BrowserStack MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@browserstack/mcp-server"
],
"env": {
"BROWSERSTACK_ACCESS_KEY": "<YOUR_BROWSERSTACK_ACCESS_KEY>",
"BROWSERSTACK_USERNAME": "<BROWSERSTACK_USERNAME>"
}
}
}
}Install BrowserStack MCP in VS Code
.vscode/mcp.json
{
"servers": {
"mcp-server": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@browserstack/mcp-server"
],
"env": {
"BROWSERSTACK_ACCESS_KEY": "<YOUR_BROWSERSTACK_ACCESS_KEY>",
"BROWSERSTACK_USERNAME": "<BROWSERSTACK_USERNAME>"
}
}
}
}Install BrowserStack MCP in VS Code CLI
$ code --add-mcp '{"name":"mcp-server","type":"stdio","command":"npx","args":["-y","@browserstack/mcp-server"],"env":{"BROWSERSTACK_ACCESS_KEY":"<YOUR_BROWSERSTACK_ACCESS_KEY>","BROWSERSTACK_USERNAME":"<BROWSERSTACK_USERNAME>"}}'Install BrowserStack MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@browserstack/mcp-server"
],
"env": {
"BROWSERSTACK_ACCESS_KEY": "<YOUR_BROWSERSTACK_ACCESS_KEY>",
"BROWSERSTACK_USERNAME": "<BROWSERSTACK_USERNAME>"
}
}
}
}Install BrowserStack MCP in Codex
$ codex mcp add mcp-server --env 'BROWSERSTACK_ACCESS_KEY=<YOUR_BROWSERSTACK_ACCESS_KEY>' --env 'BROWSERSTACK_USERNAME=<BROWSERSTACK_USERNAME>' -- npx -y @browserstack/mcp-serverInstall BrowserStack MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.mcp-server] command = "npx" args = ["-y", "@browserstack/mcp-server"] [mcp_servers.mcp-server.env] BROWSERSTACK_ACCESS_KEY = "<YOUR_BROWSERSTACK_ACCESS_KEY>" BROWSERSTACK_USERNAME = "<BROWSERSTACK_USERNAME>"
Install BrowserStack MCP in Gemini CLI
$ gemini mcp add -s user -e 'BROWSERSTACK_ACCESS_KEY=<YOUR_BROWSERSTACK_ACCESS_KEY>' -e 'BROWSERSTACK_USERNAME=<BROWSERSTACK_USERNAME>' mcp-server npx -- -y @browserstack/mcp-serverInstall BrowserStack MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"mcp-server": {
"command": "npx",
"args": [
"-y",
"@browserstack/mcp-server"
],
"env": {
"BROWSERSTACK_ACCESS_KEY": "<YOUR_BROWSERSTACK_ACCESS_KEY>",
"BROWSERSTACK_USERNAME": "<BROWSERSTACK_USERNAME>"
}
}
}
}Configuration
BROWSERSTACK_ACCESS_KEYRequiredSecretBrowserStack Access Key
BROWSERSTACK_USERNAMERequiredBrowserStack Username
| Name | Description | |
|---|---|---|
| BROWSERSTACK_ACCESS_KEY | BrowserStack Access Key | RequiredSecret |
| BROWSERSTACK_USERNAME | BrowserStack Username | Required |
Automated checks
Ran Nov 12, 2026Full report βPassed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledNot checked
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubBrowserStack MCP Server
Manage test cases, execute manual or automated tests, debug issues, and even fix codeβdirectly within tools like Cursor, Claude, or any MCP-enabled client, using plain English.
Test from anywhere:
Easily connect the BrowserStack Test Platform to your favourite AI tools, such as IDEs, LLMs, or agentic workflows.
Test with natural language:
Manage, execute, debug tests, and even fix code using plain English prompts.
Reduced context switching:
Stay in flowβkeep all project context in one place and trigger actions directly from your IDE or LLM.
β‘οΈ One Click MCP Setup
Click on the buttons below to install MCP in your respective IDE or assistant:
Β Β Β Β Β Β Β Β
Note: The hosted Remote MCP server (
mcp.browserstack.com) is now fully stateless over Streamable HTTP β any Streamable-HTTP client (Claude, Cursor, VS Code, ChatGPT) connects with no configuration change.
Kiro: a Kiro power for this server lives in
integrations/kiro-power. In the Kiro IDE, open the Powers panel β Add Custom Power β Import power from GitHub and enterhttps://github.com/browserstack/mcp-server/tree/main/integrations/kiro-power, or clone this repository and use Import power from a folder with that directory.
Prerequisites
- A BrowserStack account. Sign up if you don't have one; open-source projects can get a free plan.
- Your
usernameandaccess_keyfrom Account Settings.
For manual setup in any MCP client, see Install the MCP server locally or Set up the remote MCP server.
Note : Ensure you are using Node version >= 22
- Check your node version using
node --version. Recommended version:v22.15.0(LTS) - To Upgrade Node :
-
- On macOS
(Homebrew) - brew update && brew upgrade node or if using (nvm) - nvm install 22.15.0 && nvm use 22.15.0 && nvm alias default 22.15.0
- On macOS
-
- On Windows
(nvm-windows) : nvm install 22.15.0 && nvm use 22.15.0
- On Windows
- π Or directly download the Node.js LTS Installer
πͺ Agent-assisted setup
Most AI agents can add the BrowserStack MCP server, connect to it, and walk you through sign-in without manual config. Paste this prompt into your agent:
Add the BrowserStack MCP server to this agent, following the setup guide at
https://www.browserstack.com/docs/browserstack-mcp-server/get-started/remote-mcp-server
and using the server URL https://mcp.browserstack.com/mcp. Once it is added, start the
BrowserStack sign-in flow so I can log in.
To add it yourself, use your client's command or menu:
| Client | Command or configuration |
|---|---|
| Claude Code | claude mcp add --scope user --transport http browserstack https://mcp.browserstack.com/mcp, then run /mcp in a session and sign in |
| Claude Desktop / claude.ai | Settings β Connectors β Add custom connector, with the URL https://mcp.browserstack.com/mcp |
| ChatGPT | Install the BrowserStack plugin |
| Codex | codex mcp add browserstack --url https://mcp.browserstack.com/mcp, then codex mcp login browserstack to sign in |
| VS Code / GitHub Copilot | code --add-mcp '{"name":"browserstack","type":"http","url":"https://mcp.browserstack.com/mcp"}', then start the server from the MCP view and sign in |
| Cursor | Add "browserstack": { "url": "https://mcp.browserstack.com/mcp" } under mcpServers in ~/.cursor/mcp.json, then sign in from Cursor Settings β MCP |
| Any other MCP client | Point it at https://mcp.browserstack.com/mcp |
π‘ Usage Examples
π± Manual App Testing
Test mobile apps on real devices across the latest OS versions. Reproduce bugs and debug crashes without setup hassles. Below are some sample prompts to use your mobile apps on BrowserStack's extensive cloud of real devices
# Open app on specific device
"open my app on a iPhone 15 Pro Max"
# Debug app crashes
"My app crashed on Android 14 device, can you help me debug?"
- Unlike emulators, test your app's real-world performance on actual devices. With advanced App-Profiling features, you can debug crashes and performance issues in real-time.
- Access all major devices and OS versions from our device grid, We have strict SLAs to provision our global datacenters with newly released devices on launch day.
π Manual Web Testing
Similar to the app testing, you can use the following prompts to test your websites on BrowserStack's extensive cloud of real browsers and devices. Don't have Edge browser installed on your machine ? We've got you covered!
# Test your websites
"open my website hosted on localhost:3001 on Edge"
"open browserstack.com on latest version of Chrome"
- Test websites across different browsers and devices. We support every major browser across every major OS.
- Seamlessly test websites hosted locally on your machine, no need to deploy to a remote server!
π§ͺ Automated Testing (Playwright, Selenium, A11y and more..)
Auto-analyze, diagnose, and even fix broken test scripts right in your IDE or LLM. Instantly fetch logs, identify root causes, and apply context-aware fixes. No more debugging loops. Below are few example prompts to run/debug/fix your automated tests on BrowserStack's Test Platform.
Note: When fetching Root Cause Analysis (RCA) for a test, the server returns the suggested fix as a proposal only. It never applies code changes automatically β your assistant must present the suggestion and wait for your explicit approval before editing any files.
#Port test suite to BrowserStack
"Setup test suite to run on BrowserStack infra"
#Run tests on BrowserStack
βRun my tests on BrowserStackβ
#AI powered debugging of test failures
"My App Automate tests have failed, can you help me fix the new failures?"
- Fix test failures reported by your CI/CD pipeline by utilising our industry leading Test Observability features. Find more info here.
- Run tests written in Jest, Playwright, Selenium, and more on BrowserStack's Test Platform
π Accessibility
Catch accessibility issues early with automated, local a11y scans. Get one-click, AI-suggested fixes. No docs hunting, no CI surprises. Ensure WCAG and ADA compliance with our Accessibility Testing tool
#Scan accessibility issues while development
"Scan & help fix accessibility issues for my website running locally on localhost:3000"
#Scan accessibility issues on production site
βRun accessibility scan & identify issues on my website - www.bstackdemo.comβ
π Test Management
Create and manage test cases, create test plans and trigger test runs using natural language. Below are a few example prompts to utilise capabilities of BrowserStack's Test Management with MCP server.
# Create project & folder structure
"create new Test management project named My Demo Project with two sub folders - Login & Checkout"
# Add test cases
"add invalid login test case in Test Management project named My Demo Project"
# List added test cases
"list high priority Login test cases from Test Management project - My Demo Project"
# Create test run
"create a test run for Login tests from Test Management project - My Demo Project"
# Update test results
"update test results as passed for Login tests test run from My Demo Project"
β‘ Load Testing
Run and analyse load tests at scale without leaving your IDE or chat β find tests, start and stop runs, read reports and AI Insights, compare runs, and check your VU-hours. Works with API (JMeter, k6, Gatling, Locust), browser (Playwright, Selenium, WebdriverIO, Nightwatch) and hybrid load tests on BrowserStack's Load Testing. These go through the core tools.
# Find a test
"find my load test called checkout-api"
# Run it
"run checkout-api for 5 minutes with 100 virtual users"
# Check on it
"is my checkout-api run finished yet?"
# Read the results
"what was the p95 response time and error rate of the last checkout-api run?"
# Compare two runs of the same test
"did the latest checkout-api run regress compared with the previous one?"
# Check quota before a big run
"how many VU-hours do I have left, and what would a 30-minute run with 500 VUs cost?"
π§ͺ Access BrowserStack AI agents
Generate test cases from PRDs, convert manual tests to low-code automation, and auto-heal flaky scripts powered by BrowserStackβs AI agents, seamlessly integrated into your workflow. Below are few example prompts to access Browserstack AI agents
#Test case generator agent
"With Browserstack AI, create relevant test cases for my PRD located at /usr/file/location"
#Low code authoring agent
βWith Browserstack AI, automate my manual test case X, added in Test Managementβ
#Self healing agent
βHelp fix flaky tests in my test script with Browserstack AI self healingβ
π§ Core Tools
Five core tools let your AI assistant find and run any BrowserStack workflow. Your assistant loads every tool an MCP server exposes at the start of each session, so one tool per workflow would fill your context window and slow down the whole session. Instead, your assistant uses the core tools to search a catalog of BrowserStack tools in plain language and run the one it needs.
| Tool | Description |
|---|---|
listProducts |
Lists the BrowserStack products in the catalog, with a short summary of what each product covers |
describeEntity |
Explains one entity: its aliases, ID format, parent and related entities, and the capabilities that act on it |
searchCapability |
Finds the capabilities that match a plain-language request, with everything your assistant needs to run each one |
describeCapability |
Returns the full details of one capability, such as its parameters, request body and response format |
invokeCapability |
Runs one capability and returns the product's response unchanged. Changes to data need your approval |
See Core tools for parameters and how changes to data are approved.
All tools β See docs/TOOLS.md for every tool organised by product, or BrowserStack MCP tools & workflows for product workflows.
File & app uploads: tools that upload a local file/app (
uploadProductRequirementFile,takeAppScreenshot,runAppTestsOnBrowserStack,runAppLiveSession) require theMCP_UPLOAD_BASE_DIRenv var set to a directory containing those files; uploads are restricted to it.
π Remote MCP Server
Remote MCP comes with all the functionalities of an MCP server without the hassles of complex setup or local installation.
Key benefits:
-
β Works seamlessly in enterprise networks without worrying about firewalls or binaries or where local installation is not allowed.
-
β Secure OAuth integration β no password sharing or manual credential handling.
Limitations:
- β No Local Testing support (cannot test apps behind VPNs, firewalls, or localhost). If you have to do Local Testing, you would have to use a BrowserStack Local MCP server.
- β Latency can be slightly higher, but nothing considerable β you generally wonβt notice it in normal use.
β οΈ Important Notes
- The BrowserStack MCP Server is under active development and currently supports a subset of the MCP spec. More features will be added soon.
- Tool invocations rely on the MCP Client which in turn relies on an LLM, hence there can be some non-deterministic behaviour that can lead to unexpected results. If you have any suggestions or feedback, please open an issue to discuss.
π Contributing
We welcome contributions! Please open an issue to discuss any changes you'd like to make. π Click here to view our Contributing Guidelines
π Support
For support, please:
- Open an issue in our GitHub repository if you face any issues related to the MCP Server.
- Contact our support team for any other queries.
- Email support@browserstack.com.
- Privacy policy: browserstack.com/privacy.
π More Features Coming Soon
Stay tuned for exciting updates! Have any suggestions? Please open an issue to discuss.
BrowserStack MCP questions
How do I add BrowserStack MCP to Claude Code?
Run claude mcp add --env 'BROWSERSTACK_ACCESS_KEY=<YOUR_BROWSERSTACK_ACCESS_KEY>' --env 'BROWSERSTACK_USERNAME=<BROWSERSTACK_USERNAME>' mcp-server -- npx -y @browserstack/mcp-server in your terminal. Add --scope user to make it available in every project.
How do I add BrowserStack MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How do I authenticate the BrowserStack MCP server?
You need a BrowserStack account and your username and access_key from Account Settings; sign-in flows are also supported for hosted clients.
What Node version does the BrowserStack MCP server require?
It requires Node version 22 or later, with v22.15.0 LTS recommended.
Can I test websites hosted locally on my machine?
Yes, you can open and test sites running on localhost without deploying them to a remote server.
Can the server run automated test suites like Playwright and Selenium?
Yes, it can set up and run Jest, Playwright, Selenium, and other suites on BrowserStack's Test Platform and help debug failures.
Does the server apply code fixes automatically when debugging?
No, root cause analysis fixes are returned as proposals only and require your explicit approval before any file is edited.