Skip to main content
Glama
deenesjakoruzh
browserstack

BrowserStack MCP server

Official
by browserstack
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

BrowserStack MCP Server

Manage test cases, execute manual or automated tests, debug issues, and even fix code—directly 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 flow—keep all project context in one place and trigger actions directly from your IDE or LLM.

⚡️ One Click MCP Setup

Click on the buttons below to install MCP in your respective IDE:

   

Note: The hosted Remote MCP server (mcp.browserstack.com) is now fully stateless over Streamable HTTP — any Streamable-HTTP client (Claude, Cursor, VS Code, ChatGPT) connects with no configuration change.

Note : Ensure you are using Node version >= 18.0

  • Check your node version using node --version. Recommended version: v22.15.0 (LTS)

  • To Upgrade Node :

    1. 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

    1. On Windows (nvm-windows) : nvm install 22.15.0 && nvm use 22.15.0

  • 👉 Or directly download the Node.js LTS Installer

.

Related MCP server: Portainer MCP

💡 Usage Examples

📱 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.

🌐 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!

🧪 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 — 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
“Run my tests on BrowserStack”

#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

🌐 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
“Run accessibility scan & identify issues on my website - www.bstackdemo.com”

📋 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"

🧪 Access BrowserStack AI agents

Generate test cases from PRDs, convert manual tests to low-code automation, and auto-heal flaky scripts powered by BrowserStack’s 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
“With Browserstack AI, automate my manual test case X, added in Test Management”


#Self healing agent
“Help fix flaky tests in my test script with Browserstack AI self healing”

🛠️ Installation

📋 Prerequisites for MCP Setup

Note : Ensure you are using Node version >= 18.0

  • Check your node version using node --version. Recommended version: v22.15.0 (LTS)

One Click MCP Setup

Click on the buttons below to install MCP in your respective IDE:

   

Alternate ways to Setup MCP server

  1. Create a BrowserStack Account

    • Sign up for BrowserStack if you don't have an account already.

    • ℹ️ If you have an open-source project, we'll be able to provide you with a free plan.

    • Once you have an account (and purchased appropriate plan), note down your username and access_key from Account Settings.

  2. Note : Ensure you are using Node version >= 18.0

    • Check your node version using node --version. Recommended version: v22.15.0 (LTS)

  3. Install the MCP Server

    • VSCode (Copilot - Agent Mode): .vscode/mcp.json:

      • Locate or Create the Configuration File: In the root directory of your project, look for a folder named .vscode. This folder is usually hidden so you will need to find it as mentioned in the expand.

      • If this folder doesn't exist, create it.

      • Inside the .vscode folder, create a new file named mcp.json

      • Add the Configuration: Open the mcp.json file and then add the following JSON content.

      • Replace the username and with your BrowserStack credentials.

    {
  "servers": {
    "browserstack": {
      "command": "npx",
      "args": ["-y", "@browserstack/mcp-server@latest"],
      "env": {
        "BROWSERSTACK_USERNAME": "<username>",
        "BROWSERSTACK_ACCESS_KEY": "<access_key>"
      }
    }
  }
}

    • In VSCode, make sure to click on Start button in the MCP Server to start the server. Start MCP Server

    ** Alternate way to setup MCP on VSCode Copilot

    1.Click on the gear icon to Select Tools 2. A tool menu would appear at the top-centre, scroll down on the menu at the top and then Click on Add MCP Server 3. Select NPM package option (Install fron an NPM package) - 3rd in the list 4. Enter NPM Package Name (@browserstack/mcp-server) 5. Enter browserstack user name and access key

    • For Cursor: .cursor/mcp.json:

    {
  "mcpServers": {
    "browserstack": {
      "command": "npx",
      "args": ["-y", "@browserstack/mcp-server@latest"],
      "env": {
        "BROWSERSTACK_USERNAME": "<username>",
        "BROWSERSTACK_ACCESS_KEY": "<access_key>"
      }
    }
  }
}

    • Claude Desktop: ~/claude_desktop_config.json:

    {
  "mcpServers": {
    "browserstack": {
      "command": "npx",
      "args": ["-y", "@browserstack/mcp-server@latest"],
      "env": {
        "BROWSERSTACK_USERNAME": "<username>",
        "BROWSERSTACK_ACCESS_KEY": "<access_key>"
      }
    }
  }
}

    • Cline

Click the “MCP Servers” icon in the navigation bar Select the “Installed” tab. Click the “Configure MCP Servers” button at the bottom of the pane.

{
  "mcpServers": {
    "browserstack": {
      "command": "npx",
      "args": ["-y", "@browserstack/mcp-server@latest"],
      "env": {
        "BROWSERSTACK_USERNAME": "<username>",
        "BROWSERSTACK_ACCESS_KEY": "<access_key>"
      }
    }
  }
}

💡 List of BrowserStack MCP Tools

As of now we support 44 tools.

Remote MCP note: Tools marked (not available in Remote MCP) rely on local file/process state and are disabled in the multi-tenant Remote MCP Server. They are available in the local (npx) setup.

🧾 Test Management

  1. createProjectOrFolder — Create a Test Management project and/or folders to organize test cases. Returns with Folder ID, Project ID and Test Management Link to access the TM Project Dashboard. Prompt example

Create a new Test Management project named 'Shopping App' with two folders - Login and Checkout

  1. createTestCase — Add a manual test case under a specific project/folder (uses project identifier like PR-xxxxx and a folder ID). Prompt example

Add a test case named 'Invalid Login Scenario' to the Login folder in the 'Shopping App' project with PR-53617, Folder ID: 117869

  1. updateTestCase — Update an existing test case. Any subset of fields may be changed (name, priority, status, steps, tags, etc.); only supplied fields are modified. Prompt example

Update test case TC-482 in the 'Shopping App' project and set its priority to high

  1. listTestCases — List test cases for a project, optionally scoped to a folder (supports filters like case_type, priority, and pagination). Prompt example

List all high-priority test cases in the 'Shopping App' project with project_identifier: PR-59457

  1. listFolders — List folders in a Test Management project (returns each folder's id, name, case counts, and sub-folder counts). Pass a parent_id to list sub-folders. Prompt example

List all folders in the 'Shopping App' project with project_identifier: PR-59457

  1. listTestCaseTemplates — List test-case templates with their numeric template_id, for use with createTestCase to apply a custom template. Prompt example

List the available test case templates in the 'Shopping App' project

  1. createTestRun — Create a test run (suite) for selected test cases in a project. Prompt example

Create a test run for the Login folder in the 'Shopping App' project and name it 'Release v1.0 Login Flow'

  1. listTestRuns — List test runs for a project (filter by dates, assignee, state). Prompt example

List all test runs from the 'Shopping App' project that were executed last week and are currently marked in-progress

  1. updateTestRun — Update a test run's name/state and/or add test cases to it. Prompt example

Update test run ID 1043 in the 'Shopping App' project and mark it as complete with the note 'Regression cycle done'

  1. addTestResult — Add a manual execution result (passed/failed/blocked/skipped) for a test case within a run. Prompt example

Mark the test case 'Invalid Login Scenario' as passed in test run ID 1043 of the 'Shopping App' project

  1. createTestCasesFromFile — Generate test cases in bulk from an uploaded file using the Test Case Generator AI Agent. (not available in Remote MCP) Prompt example

Upload test cases from '/Users/xyz/testcases.pdf' to the 'Shopping App' project in Test Management

  1. listTestPlans — List test plans (TP-*) in a project, with name, status, dates, and active/closed run counts. Supports pagination. Prompt example

List all test plans in the 'Shopping App' project with project_identifier: PR-59457

  1. getTestPlan — Fetch a test plan by identifier (TP-*) with its metadata, linked test runs, total test-case count, and status summary. Prompt example

Get the details of test plan TP-120 in the 'Shopping App' project

  1. listSubTestPlans — List sub-test-plans (STP-) under a parent test plan (TP-). Supports pagination. Prompt example

List sub-test-plans under test plan TP-120 in the 'Shopping App' project

  1. getSubTestPlan — Fetch a sub-test-plan (STP-*) under a parent plan, with its metadata and linked test runs. Prompt example

Get sub-test-plan STP-45 under test plan TP-120 in the 'Shopping App' project

⚙️ BrowserStack SDK Setup / Automate Test

  1. setupBrowserStackAutomateTests — Integrate BrowserStack SDK and run web tests on BrowserStack. For visual testing/Percy, use the dedicated Percy tools. Prompt example

Run my Selenium-JUnit5 tests written in Java on Chrome and Firefox.

  1. fetchAutomationScreenshots — Fetch screenshots captured during a given Automate/App Automate session. Prompt example

Get screenshots from Automate session ID abc123xyz for my desktop test run

🔍 Observability

  1. getFailureLogs — Retrieve error logs for Automate/App Automate sessions (optionally by Build ID for App Automate). Prompt example

Get the error logs from the session ID: 21a864032a7459f1e7634222249b316759d6827f, Build ID: dt7ung4wmjittzff8kksrjadjax9gzvbscoyf9qn of App Automate test session

  1. fetchBuildInsights — Fetch insights about a BrowserStack build by combining build details and quality-gate results. Prompt example

Get the build insights for build UUID <your-build-uuid> on BrowserStack

📱 App Live

  1. runAppLiveSession — Start a manual app testing session on a real device in the cloud. Prompt example

Open my app on iPhone 15 Pro Max with iOS 17. App path is /Users/xyz/app.ipa

💻 Live

  1. runBrowserLiveSession — Start a Live session for website testing on desktop or mobile browsers. Prompt example

Open www.google.com on the latest version of Microsoft Edge on Windows 11

📲 App Automate

  1. takeAppScreenshot — Launch the app on a specified device and capture a quick verification screenshot to confirm your app has launched. Prompt example

Take a screenshot of my app on Google Pixel 6 with Android 12 while testing on App Automate. App file path: /Users/xyz/app-debug.apk

  1. runAppTestsOnBrowserStack — Run pre-built native mobile test suites (Espresso/XCUITest) by direct upload of compiled .apk/.ipa test files. Prompt example

Run Espresso tests from /tests/checkout.zip on Galaxy S21 and Pixel 6 with Android 12. App path is /apps/beta-release.apk under project 'Checkout Flow'

  1. setupBrowserStackAppAutomateTests — Set up BrowserStack App Automate SDK integration for Appium-based mobile app testing. Prompt example

Set up my Appium test suite to run on BrowserStack App Automate

♿ Accessibility

  1. accessibilityExpert — Ask the A11y Expert (WCAG 2.0/2.1/2.2, mobile/web usability, best practices). Prompt example

What WCAG guidelines apply to form field error messages on mobile web?

  1. startAccessibilityScan — Start a web accessibility scan and retrieve a local CSV report path. Prompt example

Run accessibility scan for "www.example.com"

  1. createAccessibilityAuthConfig — Create an authentication configuration (form-based or basic) for accessibility scans behind a login. Prompt example

Create a basic-auth accessibility config named 'site-login' for https://www.example.com with username testuser and password <password>

  1. getAccessibilityAuthConfig — Retrieve an existing accessibility authentication configuration by ID. Prompt example

Get accessibility auth config with ID <config-id>

  1. fetchAccessibilityIssues — Fetch accessibility issues from a completed scan, with pagination support. Prompt example

Fetch the accessibility issues for scan ID <scan-id> and scan run ID <scan-run-id>

🎨 Percy Visual Testing

  1. percyVisualTestIntegrationAgent — Integrate Percy visual testing into a new project and demonstrate visual change detection with a step-by-step simulation. Prompt example

Integrate Percy for this project

  1. expandPercyVisualTesting — Set up or expand Percy visual testing coverage for existing projects (Percy Web Standalone and Percy Automate). Prompt example

Expand Percy coverage for this project

  1. addPercySnapshotCommands — Add Percy snapshot commands to the specified test files. (not available in Remote MCP) Prompt example

Add Percy snapshot commands to my Cypress test files

  1. listTestFiles — List all test files for a given set of directories. (not available in Remote MCP) Prompt example

List the test files under my ./tests directory

  1. runPercyScan — Run a Percy visual test scan. (not available in Remote MCP) Prompt example

Run this Percy build

  1. fetchPercyChanges — Retrieve and summarize visual changes detected by Percy AI between the latest and previous builds. Prompt example

Summarize the visual changes Percy detected in my latest build

  1. managePercyBuildApproval — Approve or reject a Percy build. Prompt example

Approve the latest Percy build

🤖 BrowserStack AI Agents

  1. uploadProductRequirementFile — Upload a PRD/screenshot/PDF and get a file mapping ID (used with createTestCasesFromFile). (not available in Remote MCP) Prompt example

Upload PRD from /Users/xyz/Desktop/login-flow.pdf and use BrowserStack AI to generate test cases

  1. createLCASteps — Generate Low Code Automation (LCA) steps from a manual test case in Test Management. Prompt example

Convert the manual test case 'Add to Cart' in the 'Shopping App' project into LCA steps

  1. fetchSelfHealedSelectors — Retrieve AI self-healed selectors (plus test source) to fix flaky tests caused by DOM changes. Prompt example

Fetch and fix flaky test selectors in Automate session ID session_9482 using MCP

  1. prepareSelfHealingPlan — Build a self-healing edit plan that bundles locator pairs with test source for your LLM to apply. Does NOT modify files itself. Prompt example

Prepare a self-healing plan from the self-healed selectors for my build

  1. fetchRCA — Fetch AI Root Cause Analysis for your failed Automate/App-Automate tests (by numeric test ID). Suggests fixes only; never auto-applies. Prompt example

Fetch the root cause analysis for failed test IDs 101 and 102 on BrowserStack

  1. getBuildId — Get the BrowserStack build ID for a given project and build name, scoped to your builds. Prompt example

Get the build ID for build 'nightly-regression' in project 'Checkout Flow'

  1. listBuildId — Get the latest build ID for a project and build name, across all users (no user filter). Prompt example

Get the latest build ID for build 'nightly-regression' in project 'Checkout Flow'

  1. listTestIds — List test IDs from a BrowserStack Automate build, filtered by status (passed/failed/pending/skipped). Prompt example

List the failed test IDs from build UUID <your-build-uuid> on BrowserStack

🚀 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:

  • ✅ Works seamlessly in enterprise networks without worrying about firewalls or binaries or where local installation is not allowed.

  • ✅ Secure OAuth integration – no password sharing or manual credential handling.

Limitations:

  • ❌ 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.

  • ❌ Latency can be slightly higher, but nothing considerable — you generally won’t notice it in normal use.

Installation Steps:

  • On VSCode (Copilot - Agent Mode): .vscode/mcp.json:

    • Locate or Create the Configuration File:

    • In the root directory of your project, look for a folder named .vscode. This folder is usually hidden so you will need to find it as mentioned in the expand.

    • If this folder doesn't exist, create it.

    • Inside the .vscode folder, create a new file named mcp.json

    • To setup Remote BrowserStack MCP instead of local BrowserStack MCP you can add the following JSON content :

      Alternative way to Setup Remote MCP

    • Step 1.Click on the gear icon to Select Tools

    • Step 2. A tool menu would appear at the top-centre, scroll down on the menu at the top and then Click on Add MCP Server

    • Step 3. Click on HTTP option

    • Step 4. Paste Remote MCP Server URL : https://mcp.browserstack.com/mcp

    • Step 5. Give server id as : browserstack

    • Step 6. In VSCode Click on start MCP Server and then click on "Allow"

🤝 Recommended MCP Clients

  • We recommend using Github Copilot or Cursor for automated testing + debugging use cases.

  • For manual testing use cases (Live Testing), we recommend using Claude Desktop.

⚠️ 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.

📝 Contributing

We welcome contributions! Please open an issue to discuss any changes you'd like to make. 👉 Click here to view our Contributing Guidelines

📞 Support

For support, please:

🚀 More Features Coming Soon

Stay tuned for exciting updates! Have any suggestions? Please open an issue to discuss.

Available Tools

5 tools
getFailuresInLastRunA

Use this tool to debug failures in the last run of the test suite on BrowserStack. Use only when browserstack.yml file is present in the project root.

ParametersJSON Schema
NameRequiredDescriptionDefault
buildNameYesName of the build to get failures for. This is the 'build' key in the browserstack.yml file. If not sure, ask the user for the build name.
projectNameYesName of the project to get failures for. This is the 'projectName' key in the browserstack.yml file. If not sure, ask the user for the project name.

TDQS

A3.5/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It mentions the prerequisite (browserstack.yml file) and implies a read-only debugging function, but it lacks details on permissions, rate limits, error handling, or what the output looks like (e.g., failure details format). For a tool with no annotations, this leaves significant gaps in understanding its behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences, front-loaded with the purpose and followed by a usage condition. Every sentence adds value without redundancy, making it efficient and well-structured for quick comprehension.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and no output schema, the description is moderately complete. It covers the purpose and a key prerequisite, but it lacks details on behavioral aspects like output format, error cases, or integration with sibling tools. For a debugging tool with two required parameters, this is adequate but leaves room for improvement in contextual richness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with clear descriptions for both parameters (buildName and projectName) in the input schema. The description adds no additional parameter information beyond what the schema provides, such as examples or constraints. Baseline 3 is appropriate since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'debug failures in the last run of the test suite on BrowserStack.' It specifies the action (debug failures) and resource (test suite on BrowserStack), though it doesn't explicitly differentiate from sibling tools like 'runTestsOnBrowserStack' or 'startAccessibilityScan' beyond the debugging focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use the tool: 'Use only when browserstack.yml file is present in the project root.' This gives a prerequisite condition, but it doesn't explicitly state when not to use it or name alternatives among the sibling tools, such as when to choose this over 'runTestsOnBrowserStack' for debugging versus execution.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

runAppLiveSessionB

Use this tool when user wants to manually check their app on a particular mobile device using BrowserStack's cloud infrastructure. Can be used to debug crashes, slow performance, etc.

ParametersJSON Schema
NameRequiredDescriptionDefault
appPathYesThe path to the .ipa or .apk file to install on the device. Always ask the user for the app path, do not assume it.
desiredPhoneYesThe full name of the device to run the app on. Example: 'iPhone 12 Pro' or 'Samsung Galaxy S20' or 'Google Pixel 6'. Always ask the user for the device they want to use, do not assume it.
desiredPlatformYesWhich platform to run on, examples: 'android', 'ios'. Set this based on the app path provided.
desiredPlatformVersionYesThe platform version to run the app on. Example: '12.0' for Android devices or '16.0' for iOS devices

TDQS

B3.1/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions the tool uses BrowserStack's cloud infrastructure and can be used for debugging, but doesn't describe what happens during the session, whether it's interactive or automated, session duration limits, authentication requirements, or what output to expect. Significant behavioral details are missing for a cloud-based testing tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately concise with two sentences that efficiently convey the tool's purpose and primary use cases. It's front-loaded with the main purpose and follows with specific examples. No wasted words, though it could be slightly more structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 4 required parameters, no annotations, and no output schema, the description is insufficient. It doesn't explain what happens after the session starts, what kind of output or interface the user gets, session management, or error handling. The description leaves too many operational questions unanswered for a cloud-based testing tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already fully documents all 4 parameters. The description doesn't add any parameter-specific information beyond what's in the schema descriptions. The baseline score of 3 is appropriate when the schema does all the parameter documentation work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'manually check their app on a particular mobile device using BrowserStack's cloud infrastructure' with specific use cases like debugging crashes and slow performance. It distinguishes from sibling tools by focusing on mobile app testing rather than browser sessions or test automation, though it doesn't explicitly name alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides some usage context ('when user wants to manually check their app') and implies this is for interactive debugging rather than automated testing. However, it doesn't explicitly state when to use this vs. sibling tools like 'runTestsOnBrowserStack' or 'runBrowserLiveSession', nor does it mention any prerequisites or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

runBrowserLiveSessionB

Use this tool when user wants to manually check their website on a particular browser and OS combination using BrowserStack's cloud infrastructure. Can be used to debug layout issues, compatibility problems, etc.

ParametersJSON Schema
NameRequiredDescriptionDefault
desiredBrowserYesThe browser to run the test on. Example: 'Chrome', 'IE', 'Safari', 'Edge'. Always ask the user for the browser they want to use, do not assume it.
desiredBrowserVersionYesThe version of the browser to use. Example: 133.0, 134.0, 87.0
desiredOSYesThe operating system to run the browser on. Example: 'Windows', 'OS X'
desiredOSVersionYesThe OS version to run the browser on. Example: '10' for Windows, '12' for macOS, '14' for iOS
desiredURLYesThe URL of the website to test. This can be a local URL (e.g., http://localhost:3000) or a public URL. Always ask the user for the URL, do not assume it.

TDQS

B3.4/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden but lacks critical behavioral details. It mentions using BrowserStack's cloud infrastructure and manual checking, but doesn't disclose whether this starts a live session, requires authentication, has time/rate limits, costs, or what happens after the check. For a tool with 5 required parameters and no annotations, this is a significant gap in transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences that efficiently convey the tool's purpose and use cases without wasted words. The description is appropriately sized and front-loaded with the main purpose, though it could be slightly more structured with bullet points for use cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 5 required parameters, no annotations, and no output schema, the description provides adequate purpose and usage context but lacks completeness about behavioral aspects (e.g., session management, authentication, limitations). It's minimally viable for understanding what the tool does but insufficient for understanding how it behaves during/after execution.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 5 parameters thoroughly with examples and guidance. The description adds no parameter-specific information beyond implying these parameters are needed for browser/OS/URL selection. Baseline 3 is appropriate when schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'manually check their website on a particular browser and OS combination using BrowserStack's cloud infrastructure' with specific use cases like debugging layout issues. It distinguishes from siblings by focusing on manual website testing (vs. getFailuresInLastRun for failures, runAppLiveSession for apps, etc.), though not explicitly contrasting each sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides clear context for when to use it: 'when user wants to manually check their website on a particular browser and OS combination' for debugging layout/compatibility issues. It doesn't explicitly state when NOT to use it or name alternatives among siblings, but the context strongly implies this is for manual website testing vs. automated testing or other functions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

runTestsOnBrowserStackC

Use this tool to get instructions for running tests on BrowserStack.

ParametersJSON Schema
NameRequiredDescriptionDefault
desiredPlatformsYesThe platforms the user wants to test on. Always ask this to the user, do not try to infer this.
detectedBrowserAutomationFrameworkYesThe automation framework configured in the project. Example: 'playwright', 'selenium'
detectedLanguageYesThe programming language used in the project. Example: 'nodejs', 'python'
detectedTestingFrameworkYesThe testing framework used in the project. Example: 'jest', 'pytest'

TDQS

C2.6/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool 'get instructions' but does not clarify what form these instructions take (e.g., text, links, steps), whether it's a read-only operation, if it requires authentication, or any rate limits. This leaves significant gaps in understanding the tool's behavior beyond its basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, straightforward sentence that efficiently states the tool's purpose without unnecessary words. It is front-loaded with the core action, but could be slightly more informative to improve utility while maintaining brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of a tool with 4 required parameters and no annotations or output schema, the description is incomplete. It does not explain what the instructions entail, how they are generated, or what the user should expect as a result. This leaves too many gaps for effective agent use, especially without behavioral context or output details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents all four parameters. The description adds no additional meaning about parameters beyond what the schema provides, such as explaining why these inputs are needed for generating instructions. With high schema coverage, the baseline score of 3 is appropriate, as the description does not compensate but also does not detract.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool's purpose as 'to get instructions for running tests on BrowserStack', which is clear but vague. It specifies the action ('get instructions') and target ('running tests on BrowserStack'), but lacks specificity about what kind of instructions or how they are delivered. It does not distinguish from siblings like 'runAppLiveSession' or 'runBrowserLiveSession', which might also involve BrowserStack testing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention prerequisites, context, or exclusions, and there is no comparison to sibling tools like 'runAppLiveSession' or 'startAccessibilityScan'. Usage is implied only by the purpose, with no explicit when/when-not instructions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

startAccessibilityScanC

Use this tool to start an accessibility scan for a list of URLs on BrowserStack.

ParametersJSON Schema
NameRequiredDescriptionDefault
nameYesName of the accessibility scan
pageURLYesThe URL to scan for accessibility issues

TDQS

C2.9/5.0
Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool starts a scan but doesn't describe what the scan entails (e.g., duration, asynchronous nature, permissions required, rate limits, or what 'start' implies in terms of immediate results). This is a significant gap for a tool that likely initiates a process.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence that directly states the tool's purpose. It's front-loaded and wastes no words, though it could be slightly more structured if it included key behavioral details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of starting a scan (likely an asynchronous operation) with no annotations and no output schema, the description is incomplete. It doesn't explain what happens after starting the scan, expected outputs, error handling, or how to retrieve results, leaving critical gaps for agent usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with clear descriptions for both parameters ('name' and 'pageURL'). The description mentions 'a list of URLs' but the schema only has one 'pageURL' parameter, which adds minor confusion. However, since the schema already documents parameters well, the baseline score of 3 is appropriate as the description doesn't add meaningful semantic details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('start an accessibility scan') and the target ('for a list of URLs on BrowserStack'), providing a specific verb+resource combination. However, it doesn't explicitly distinguish this tool from sibling tools like 'runTestsOnBrowserStack' or 'runBrowserLiveSession', which might also involve scanning or testing URLs, so it misses full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites, when-not-to-use scenarios, or compare it to sibling tools like 'getFailuresInLastRun' or 'runTestsOnBrowserStack', leaving the agent without context for selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. 5 tool updatesv1.0.0
    • First observedgetFailuresInLastRun
    • First observedrunAppLiveSession
    • First observedrunBrowserLiveSession
    • First observedrunTestsOnBrowserStack
    • First observedstartAccessibilityScan
Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.3/5.0
Disambiguation5/5

Each tool has a clearly distinct purpose with no overlap: getFailuresInLastRun is for debugging test failures, runAppLiveSession is for manual mobile app testing, runBrowserLiveSession is for manual website testing, runTestsOnBrowserStack is for test execution instructions, and startAccessibilityScan is for accessibility scanning. The descriptions reinforce these distinct use cases, making tool selection unambiguous.

Naming Consistency3/5

The naming follows a mixed pattern: three tools use 'run' as a verb (runAppLiveSession, runBrowserLiveSession, runTestsOnBrowserStack), while getFailuresInLastRun uses 'get' and startAccessibilityScan uses 'start'. All tools use camelCase consistently, but the verb choices vary, creating a readable but not fully consistent convention across the set.

Tool Count5/5

With 5 tools, this is well-scoped for a BrowserStack testing server. Each tool serves a distinct and essential function in the testing workflow—debugging, manual testing (app and browser), test execution, and accessibility scanning—making the count appropriate without being too sparse or bloated.

Completeness4/5

The toolset covers key BrowserStack functionalities: debugging failures, manual testing for apps and browsers, test execution guidance, and accessibility scanning. Minor gaps might include automated test reporting or configuration management, but the core workflows are well-covered, allowing agents to perform most common testing tasks effectively.

Maintenance

ActivityActive
ResponsivenessUnresponsive

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/browserstack/mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server