TestingBot MCP Server
OfficialProvides the bundled appium-mcp toolset for automating native mobile apps on real iOS and Android devices through TestingBot, including session management, gestures, element interaction, and screenshots.
TestingBot MCP Server
TestingBot's official Model Context Protocol (MCP) server implementation. This server enables AI assistants to interact with TestingBot's testing infrastructure, allowing you to manage tests, browsers, devices, and more through conversational interfaces.
โก One-Click Install
Claude Desktop: download testingbot-mcp-server-<version>.mcpb from the latest release and double-click it. Claude will set up the TestingBot MCP server automatically.
After install, set your credentials from TestingBot account settings.
Related MCP server: Argus MCP Server
Features
๐ฑ App Automate - Run Maestro, Espresso, and XCUITest suites on real devices and emulators, straight from the agent
๐ฅ๏ธ Live Testing - Start interactive manual testing sessions on real browsers and devices
๐ Browser & Device Management - Query available browsers and real devices
๐งช Test Management - Create, retrieve, update, and delete tests with comprehensive details
๐ฆ Storage Management - Upload and manage mobile app files (APK, IPA, ZIP)
๐ธ Screenshot Testing - Take cross-browser screenshots
๐๏ธ Build Management - Organize tests into builds
๐ค User Account - View and update account information
๐ฅ Team Management - Manage team settings and team members
๐ Chrome DevTools Protocol - Create CDP sessions for advanced browser automation
๐ Tunnel Management - Start, stop and manage TestingBot tunnels to test localhost and private sites
Prerequisites
Node.js >= 20 (recommended: 22.15.0 or later)
TestingBot Account with API credentials
An MCP-compatible client (Claude Desktop, VS Code with Continue, Cursor, etc.)
Installation
Quick Setup
Install the MCP server globally:
npm install -g @testingbot/mcp-serverOr add to your project:
npm install @testingbot/mcp-serverConfiguration
Recommended: log in with tb_login (no key/secret to copy)
You don't have to find and paste API credentials. Install the server, leave the credentials blank, and just ask the agent:
Log me in to TestingBot.
The agent calls the tb_login tool. It uses OAuth-style browser
authentication โ no secret ever leaves the browser โ and picks the right
mechanism for your environment automatically:
Browser (loopback, the default on a desktop): your browser opens to a TestingBot authorization page. Sign in if needed and click Authorize; the credentials are captured on a local callback and the agent finishes the sign-in. Nothing to type. (RFC 8252.)
Device code (automatic fallback on SSH / remote / dev containers / web): the tool prints a short URL and code instead:
Open the URL in your browser (e.g.
https://testingbot.com/device).Enter the code, sign in if needed, and click Authorize.
Tell the agent you've authorized โ it calls
tb_loginagain to finish.
(RFC 8628.)
You can force a mechanism by passing mode: "loopback" or mode: "device" to
tb_login (the default is "auto").
Your credentials are written to ~/.testingbot/credentials (mode 0600) and
used by every subsequent tool call โ no restart and no JSON editing. This works
in any MCP client (VS Code, Cursor, Cline, Claude Desktop, โฆ). To use a different
account, set TESTINGBOT_PROFILE; to relocate the file, set
TESTINGBOT_CONFIG_DIR.
Environment Variables
Alternatively (or for CI, where env vars take precedence over the file), set your TestingBot credentials as environment variables:
export TESTINGBOT_KEY="your-api-key"
export TESTINGBOT_SECRET="your-api-secret"Or create a .env file in your project:
TESTINGBOT_KEY=your-api-key
TESTINGBOT_SECRET=your-api-secretThe key also accepts the aliases TB_KEY / TESTINGBOT_USERNAME, and the secret
accepts TB_SECRET / TESTINGBOT_ACCESS_KEY.
How credentials are resolved
Credentials are resolved in this order, highest priority first:
Environment variables (above) โ both a key and a secret must be set. This lets CI and per-client config override everything else.
The
~/.testingbot/credentialsfile written bytb_login, for the active profile (default, orTESTINGBOT_PROFILE).Neither set: the server starts in a degraded mode where every tool except
tb_loginreports "Run tb_login to authenticate" โ so first run is self-healing rather than a hard error.
Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%/Claude/claude_desktop_config.json (Windows):
{
"mcpServers": {
"testingbot": {
"command": "npx",
"args": ["-y", "@testingbot/mcp-server"],
"env": {
"TESTINGBOT_KEY": "your-api-key",
"TESTINGBOT_SECRET": "your-api-secret"
}
}
}
}VS Code (with Continue extension)
Add to .continue/config.json:
{
"mcpServers": [
{
"name": "testingbot",
"command": "npx",
"args": ["-y", "@testingbot/mcp-server"],
"env": {
"TESTINGBOT_KEY": "your-api-key",
"TESTINGBOT_SECRET": "your-api-secret"
}
}
]
}Cursor
Add to .cursor/mcp.json:
{
"mcpServers": {
"testingbot": {
"command": "npx",
"args": ["-y", "@testingbot/mcp-server"],
"env": {
"TESTINGBOT_KEY": "your-api-key",
"TESTINGBOT_SECRET": "your-api-secret"
}
}
}
}๐ค Let an AI Agent Drive a Remote Browser or Device
This server already includes the automation tools from @testingbot/automation-mcp โ installing this package gives the agent the ability to actually drive a remote browser or real mobile device on TestingBot's grid, not just manage resources.
Just ask:
Open Safari 17 on macOS on TestingBot. Navigate to example.com and click the "More information" link.
The agent will call tb_openBrowser, tb_navigate, tb_snapshot, tb_click โ and surface a live-view URL so you can watch it in real time. For real iOS / Android devices, the bundled appium-mcp child gives the agent the full appium_* toolbelt (appium_session_management, appium_gesture, appium_set_value, appium_screenshot, ~30 more) โ no separate install or config required. Just ask: "Open an iPhone 15 Pro on iOS 17 on TestingBot, tap the login button, take a screenshot." See the @testingbot/automation-mcp README for the full tool list, caveats (sessions are metered), and configuration options.
๐ Testing localhost and private sites
TestingBot's browsers and devices run in the cloud, so they can't open localhost, private IPs (10.x, 192.168.x, โฆ) or intranet hosts directly. To reach them, they need a TestingBot Tunnel running on your machine. Just ask:
Start a tunnel and open http://localhost:3000 in Chrome on Windows 11.
The agent calls startTunnel, which needs Java 17+. The tool returns the tunnel's identifier and ID, and the agent passes them on:
Run | How it uses the tunnel |
|
|
|
|
|
|
|
|
| The account's newest running tunnel is used automatically |
Android apps and flows: Android never sends localhost / 127.0.0.1 through a proxy, so on an Android device or emulator those URLs reach the device itself, not your machine. Use a hostname that resolves to 127.0.0.1 on your side instead, such as http://myapp.localtest.me:3000. The tunnel resolves it on your machine.
stopTunnel stops the tunnel. Tunnels started by the server are also stopped when the server exits. If you'd rather run the tunnel yourself, start it with --tunnel-identifier <name> and give the agent that name.
Available Tools
Live Testing
startLiveSession
Start an interactive live testing session on TestingBot. Returns a link that opens the session in your TestingBot dashboard, where you confirm it with Start. Mobile sessions run on emulators/simulators; real-device live sessions are started from the dashboard.
Parameters:
platformType: "desktop" or "mobile"desiredURL: The URL to opendesiredOS: Operating system (Windows, Mac, Linux for desktop; android, ios for mobile)desiredOSVersion: OS version: Windows11/10/8.1/8; macOS by name (Sonoma) or number (14); or a platform code likeWIN11desiredBrowser(desktop only): Browser name (chrome, firefox, safari, edge, ie)desiredBrowserVersion(desktop only): Browser version or "latest"desiredDevice(mobile only): Device name (e.g., "iPhone 14", "Galaxy S23")tunnelId(optional): Numeric ID of a running tunnel, needed for localhost / private URLs (see Testing localhost and private sites)
Example prompts:
"Start a live testing session on Chrome latest with Windows 11 for https://example.com" "Open https://myapp.com on iPhone 14 with iOS 16 for manual testing"
startDesktopLiveSession
Convenience tool to start a desktop browser live testing session.
Parameters:
desiredURL: The URL to opendesiredOS: Windows, Mac, or LinuxdesiredOSVersion: OS versiondesiredBrowser: chrome, firefox, safari, edge, or iedesiredBrowserVersion(optional): Browser version or "latest" (default: latest)tunnelId(optional): Numeric ID of a running tunnel, for localhost / private URLs
Example prompt:
"Start desktop live session on Firefox 120 with Mac Monterey for https://example.com"
startMobileLiveSession
Convenience tool to start a mobile device live testing session.
Parameters:
desiredURL: The URL to opendesiredOS: android or iosdesiredOSVersion: OS versiondesiredDevice: Device nametunnelId(optional): Numeric ID of a running tunnel, for localhost / private URLs
Example prompt:
"Start mobile live session on Galaxy S23 with Android 13 for https://example.com"
Browser & Device Management
getBrowsers
Get list of available browsers and platforms for testing.
Parameters:
type(optional): Filter by "web" or "mobile"
Example prompt:
"Show me all available browsers for testing" "What mobile browsers are available?"
getDevices
Get list of available mobile devices (real devices and simulators).
Example prompt:
"List all available iOS devices" "Show me Android devices for testing"
Test Management
getTests
Retrieve a list of recent tests with pagination.
Parameters:
offset(optional): Pagination offset (default: 0)limit(optional): Number of tests to retrieve (default: 10, max: 100)
Example prompt:
"Show me my last 20 tests" "Get recent test results"
getTestDetails
Get comprehensive details about a specific test including:
Test status, browser, platform, and timing information
Video recording URL and screenshot URLs
Selenium, browser, and Appium logs
Test execution steps with commands and timestamps
Network logs, exception logs, and JS errors
Parameters:
sessionId: The session ID of the test
Example prompt:
"Get details for test session abc123" "Show me the video and logs for test xyz789" "Show execution steps for test abc123"
updateTest
Update test metadata such as name, status, or build.
Parameters:
sessionId: The session ID of the testname(optional): New name for the teststatus(optional): "passed" or "failed"build(optional): Build identifierextra(optional): Additional metadata (JSON string)
Example prompt:
"Mark test abc123 as passed" "Update test xyz789 with name 'Login Flow Test'"
deleteTest
Delete a test by session ID.
Parameters:
sessionId: The session ID of the test to delete
Example prompt:
"Delete test abc123"
stopTest
Stop a running test by session ID.
Parameters:
sessionId: The session ID of the test to stop
Example prompt:
"Stop test abc123"
AI Failure Analysis
Explanations from TestingBot AI Insights: summary, root cause, timeline, log evidence, suggested fixes, a failure category, the likely owner and a confidence score. The account owner must first enable AI Analysis in Account Settings, which records consent to sending curated, secret-masked test logs to TestingBot's AI provider; until then both tools say how to turn it on and nothing is sent.
analyzeTestFailure
Start (or reuse) an AI failure analysis of a finished test and wait for the result. A current analysis is returned without extra cost.
Parameters:
sessionId: Session ID (or numeric test ID)force(optional): Run a fresh analysis even if one existswaitSeconds(optional): How long to wait for the result (default 90, 0 returns immediately)
Example prompt:
"Why did test abc123 fail?"
getAiFailureAnalysis
Read an existing analysis. Never starts one.
Parameters:
sessionId: Session ID (or numeric test ID)
Build Management
getBuilds
Get a list of builds with pagination.
Parameters:
offset(optional): Pagination offset (default: 0)limit(optional): Number of builds to retrieve (default: 10, max: 100)
Example prompt:
"Show me my recent builds"
getTestsForBuild
Get all tests associated with a specific build ID.
Parameters:
buildId: The build ID
Example prompt:
"Show all tests for build 12345"
deleteBuild
Delete a build and all its associated tests.
Parameters:
buildId: The build ID to delete
Example prompt:
"Delete build 12345"
Storage Management
uploadFile
Upload a local file (APK, IPA, or ZIP) to TestingBot storage.
Parameters:
localFilePath: Path to the file to upload
Example prompt:
"Upload /path/to/app.apk to TestingBot"
uploadRemoteFile
Upload a file from a remote URL to TestingBot storage.
Parameters:
remoteUrl: URL of the file to upload
Example prompt:
"Upload https://example.com/app.ipa to TestingBot"
getStorageFiles
List all files in TestingBot storage.
Parameters:
offset(optional): Pagination offset (default: 0)limit(optional): Number of files to retrieve (default: 10, max: 100)
Example prompt:
"Show me all uploaded apps"
deleteStorageFile
Delete a file from TestingBot storage.
Parameters:
appUrl: The app_url of the file to delete
Example prompt:
"Delete app tb://app123 from storage"
App Automate โ Maestro
Run Maestro flows on TestingBot real devices, emulators, and simulators. Runs are asynchronous: start one, poll its status, then fetch results โ the agent is never blocked while devices execute.
uploadMaestroApp
Upload the app under test (.apk, .aab, .ipa, or zipped .app). Uploads are deduplicated by checksum โ re-running with the same binary is instant.
Parameters:
localFilePath: Local path to the app file
Returns a Project ID used by the other Maestro tools.
Example prompt:
"Upload ./build/app.apk for Maestro testing"
uploadMaestroFlows
Upload the Maestro flow YAML files for a project. Accepts a directory (structure preserved, so runFlow subflows keep working), a pre-built .zip, or inline YAML written by the agent. Replaces previously uploaded flows.
Parameters:
projectId: Project ID fromuploadMaestroAppflowsPath(optional): Directory or.zipof flow YAML filesflows(optional): Inline flows as[{ fileName, content }]
runMaestroTest
Start a Maestro run. Returns immediately with the run ID โ poll with getMaestroRunStatus.
Parameters:
projectId: Project IDplatformName: "Android" or "iOS"deviceName(optional): Device name, wildcards/regex supported (e.g."Pixel 8","iPhone 1[4-6]","*")version(optional): OS versionrealDevice(optional): Run on a physical device (required for.ipa)name(optional): Run name shown in the dashboardenv(optional): Environment variables passed to the flowsincludeTags/excludeTags(optional): Filter flows by Maestro tagsshardSplit(optional): Split flows across parallel devicesotherApps(optional): Up to 4 companion app URLs to install alongside the apptunnelIdentifier(optional): Run through this tunnel, so the app can reach localhost / private backends
Example prompt:
"Run my Maestro flows on a real Pixel 8 with Android 14"
getMaestroRunStatus
Poll run progress. Lists per-flow statuses (WAITING, READY, DONE, FAILED, CANCELLED), failures first.
getMaestroRunResults
Final results of a completed run: per-flow outcomes plus the JUnit XML report.
getMaestroFlowDetails
Deep-dive into one flow: error messages, step-level JUnit report, and links to the video, screenshots, and device logs. This is the debugging tool โ fetch it for a failed flow, fix the YAML, then retry.
Parameters: projectId, runId, flowId
cancelMaestroRun / retryMaestroRun
Cancel a running run, or retry a run โ pass flowId to retry only a single failed flow.
uploadMaestroCompanionApp
Upload a supplementary app installed alongside the app under test. Returns a tb:// URL for runMaestroTest's otherApps.
listMaestroProjects / listMaestroRuns
Discover existing projects (app, flows, run IDs) and runs across the account. listMaestroRuns accepts a buildName to look up runs by name โ e.g. "rerun whatever failed in last night's nightly build".
maestroCheatSheet
Returns a Maestro YAML syntax reference (commands, selectors, flow structure, and the TestingBot workflow). Agents call this before writing or fixing flows.
Example workflow:
User: "Run the Maestro flows in ./flows against ./app.apk on a real Pixel 8. Fix any failures."
Assistant: [uploadMaestroApp โ uploadMaestroFlows โ runMaestroTest]
Assistant: [polls getMaestroRunStatus until complete]
Assistant: [getMaestroFlowDetails for the failed flow, reads the error + screenshots]
Assistant: [fixes the flow YAML, uploadMaestroFlows, retryMaestroRun]App Automate โ Espresso & XCUITest
Run pre-built Espresso (Android) and XCUITest (iOS) suites on TestingBot devices. Same async pattern: start, poll, fetch results.
uploadAppAutomateApp
Upload the app under test: .apk/.aab for Espresso, .ipa for XCUITest.
Parameters: framework ("espresso" or "xcuitest"), localFilePath
uploadAppAutomateTests
Upload the test suite: the instrumented test .apk for Espresso, or the zipped XCUITest runner bundle.
Parameters: framework, projectId, localFilePath
runAppAutomateTest
Start a run. Returns immediately with the run ID.
Parameters:
framework,projectIddeviceName,version,realDevice,name,build(optional): device selection and metadatatestClasses,skipTestClasses,packages,annotations,testRunner(optional, Espresso only): test filteringlocale,timeZone(optional)
Example prompt:
"Run the Espresso suite on a real Galaxy S23, only the com.example.LoginTest class"
getAppAutomateRunStatus / getAppAutomateRunResults
Poll run progress, then fetch per-run outcomes and the JUnit XML report. Each run's Appium session ID is surfaced, so getTestDetails / getFailureLogs work for logs and video.
Visual Testing Review
Review hosted visual tests: find failed runs, see what changed, approve or reject. When the account owner has turned on AI region names, each changed region carries a one-line AI description of the change; reading a run never sends anything to an AI provider.
getVisualTests
List hosted visual tests. Parameters: offset, limit (optional)
getVisualRuns
List visual runs, newest first. Parameters: testId, state (failed, unreviewed, passed), offset, limit (all optional)
explainVisualRun
What changed in a run: regions with names, AI change descriptions, text and CSS changes, and image links. Parameters: runId
Example prompt:
"Which visual tests failed today, and what changed on the pricing page?"
reviewVisualRun
Approve or reject a run. Parameters: runId, decision (approve/reject), makeBaseline (optional, with approve)
Accessibility Testing
Results of scheduled accessibility scans, scored like the dashboard: WCAG A/AA violations decide pass/fail; needs-review items and best-practice recommendations do not. Automated checks cover only part of WCAG.
getAccessibilityTests
Scheduled accessibility tests with their latest result. Parameters: offset, limit (optional)
getAccessibilityRuns
Scans of one test, newest first. Parameters: testId, offset, limit
getAccessibilityFindings
Failing rules with the elements (selector, HTML, how to fix) and what is new or resolved since the previous scan. Parameters: runId, elementsPerRule (optional, default 5)
Example prompt:
"What accessibility issues does our checkout page have, and which are new since the last scan?"
runAccessibilityTest
Start a scan now. Parameters: testId
Screenshot Testing
takeScreenshot
Take screenshots of a URL across multiple browsers and platforms.
Parameters:
url: The URL to screenshotbrowsers: Array of browser configurationsbrowserName: Browser name (chrome, firefox, safari, etc.)version(optional): Browser version or "latest"os: Operating system (WIN11, MAC, etc.)
resolution(optional): Screen resolution (default: "1920x1080")waitTime(optional): Seconds to wait before screenshot (default: 5, max: 60)fullPage(optional): Capture full page or viewport (default: false)
For a localhost / private URL, the screenshots go through the account's newest running tunnel. If no tunnel is running, the tool says so instead of taking the screenshots.
Example prompt:
"Take a screenshot of https://example.com on Chrome and Firefox" "Screenshot my homepage on mobile devices"
retrieveScreenshots
Retrieve screenshot results by screenshot ID.
Parameters:
screenshotId: The screenshot ID from takeScreenshot
Example prompt:
"Get screenshots for job abc123"
getScreenshotList
Get a list of all screenshot jobs.
Parameters:
offset(optional): Pagination offset (default: 0)limit(optional): Number of jobs to retrieve (default: 10, max: 100)
Example prompt:
"Show me my recent screenshot jobs"
User Management
getUserInfo
Get current user account information including minutes used, plan details, and limits.
Example prompt:
"Show my account information" "How many minutes have I used?"
updateUserInfo
Update user account information.
Parameters:
firstName(optional): First namelastName(optional): Last nameemail(optional): Email address
Example prompt:
"Update my email to newemail@example.com"
Team Management
getTeam
Get team information including concurrency: parallel sessions allowed, running right now and queued (waiting for a free slot), for VMs and physical devices. Counts are team-wide and match the dashboard.
Example prompt:
"Show my team information" "What are my team's concurrency limits?" "How many of my tests are running or queued right now?"
getUsersInTeam
List all users in your team with their roles and access levels.
Parameters:
offset(optional): Pagination offset (default: 0)limit(optional): Number of users to retrieve (default: 10, max: 100)
Example prompt:
"Show me all team members" "List users in my team"
getUserFromTeam
Get detailed information about a specific team member by user ID.
Parameters:
userId: The user ID to retrieve
Example prompt:
"Show details for user 12345"
Chrome DevTools Protocol (CDP)
createCdpSession
Create a Chrome DevTools Protocol session for advanced browser automation. Returns a WebSocket URL to connect to the browser.
Parameters:
browserName: Browser name (chrome, firefox, safari, edge, etc.)browserVersion(optional): Browser version or "latest" (default: latest)platform: Operating system platformscreenResolution(optional): Screen resolution (e.g., "1920x1080")name(optional): Session namebuild(optional): Build identifier
Example prompt:
"Create a CDP session on Chrome latest with Windows 11" "Start a CDP session on Firefox 120 for automation"
Tunnel Management
TestingBot's browsers and devices run in the cloud. To test localhost, private IPs or intranet sites, they need a TestingBot Tunnel running on your machine. These tools can start one for you.
startTunnel
Starts a TestingBot Tunnel on the machine running the MCP server and waits until it is ready. Returns the tunnel's identifier and numeric ID. The tunnel stops with stopTunnel or when the MCP server exits. On first use the tunnel is downloaded, and it needs Java 17 or newer.
Parameters:
tunnelIdentifier(optional): Name for the tunnel. If you don't give one, a unique one is generated.shared(optional): Share the tunnel with your teamnoBump(optional): Do not re-sign HTTPS traffic (for certificate pinning or client certificates)noCache(optional): Disable caching in the tunnel
Example prompt:
"Start a tunnel and open http://localhost:3000 in Chrome on Windows 11"
stopTunnel
Stops a tunnel started with startTunnel.
Parameters:
tunnelIdentifier(optional): The tunnel to stop. Can be left out when only one tunnel is running.all(optional): Stop every tunnel this server started
getTunnelList
Get a list of all active TestingBot tunnels on your account, with their identifiers. Tunnels allow testing websites behind firewalls or on your local machine.
Example prompt:
"Show me all active tunnels" "List my TestingBot tunnels"
deleteTunnel
Delete an active TestingBot tunnel by ID. This terminates the tunnel connection.
Parameters:
tunnelId: The tunnel ID to delete
Example prompt:
"Delete tunnel 12345"
Prompts, Resources and Agent Skills
Besides tools, the server offers MCP prompts: task recipes your client can show as slash commands:
Prompt | Arguments | What it does |
|
| Test status, AI failure analysis when enabled, failing log lines, likely cause and fixes |
|
| Pass/fail counts, failures grouped by shared cause, what to fix first |
|
| Tests that both passed and failed, and why each is unstable |
and read-only resources a client can attach to a conversation:
URI | Content |
| Test details (JSON) |
| One log file, last 200 KB ( |
| Tests in a build (JSON) |
| Flaky tests over the last 30 days; |
The same recipes ship as agent skills in skills/ (one SKILL.md per task) for agents that load skills from files.
Usage Examples
Example 1: Running Cross-Browser Tests
User: "Show me all available browsers for web testing"
Assistant: [Lists all web browsers]
User: "Take a screenshot of https://myapp.com on Chrome latest and Firefox latest on Windows 11"
Assistant: [Creates screenshot job and returns ID]
User: "Get the screenshots for job abc123"
Assistant: [Returns screenshot URLs]Example 2: Managing Mobile App Tests
User: "Upload my app from https://example.com/app.apk"
Assistant: [Uploads app and returns tb://app123]
User: "Show me all my uploaded apps"
Assistant: [Lists storage files]
User: "Show me the last 10 tests"
Assistant: [Shows recent test results]Example 3: Agent-Driven Maestro Testing on Real Devices
User: "Write a Maestro flow that logs into my app and run it on a real Pixel 8"
Assistant: [maestroCheatSheet for syntax, writes the flow YAML]
Assistant: [uploadMaestroApp ./app.apk โ project 42]
Assistant: [uploadMaestroFlows with the inline flow]
Assistant: [runMaestroTest on Pixel 8 with realDevice: true โ run 101]
Assistant: [polls getMaestroRunStatus, then getMaestroRunResults]
User: "The checkout flow failed โ figure out why and fix it"
Assistant: [getMaestroFlowDetails โ reads error + screenshots + video]
Assistant: [fixes the YAML, uploadMaestroFlows, retryMaestroRun]Example 4: Build Management
User: "Show me my recent builds"
Assistant: [Lists recent builds]
User: "Show all tests for build 12345"
Assistant: [Lists tests in that build]
User: "Mark test xyz789 as passed with build name 'Release 1.0'"
Assistant: [Updates test]Example 5: Team & Tunnel Management
User: "Show me my team information"
Assistant: [Shows team concurrency limits and settings]
User: "List all team members"
Assistant: [Lists all users in the team]
User: "Show me all active tunnels"
Assistant: [Lists active TestingBot tunnels]
User: "Start a tunnel and check that http://localhost:3000 loads in Safari on macOS"
Assistant: [Starts a tunnel, opens Safari with that tunnel, loads the page]
User: "Stop the tunnel"
Assistant: [Stops the tunnel it started]Example 6: CDP Automation
User: "Create a CDP session on Chrome latest with Windows 11"
Assistant: [Creates session and returns WebSocket URL]
User: "Show me test execution steps for session abc123"
Assistant: [Shows detailed command history with timestamps]Development
Setup
# Clone the repository
git clone https://github.com/testingbot/mcp-server.git
cd testingbot-mcp-server
# Install dependencies
npm install
# Set up environment variables
cp .env.example .env
# Edit .env with your credentialsCommands
# Build the project (runs lint, format, test, and compile)
npm run build
# Development mode with watch
npm run dev
# Run tests
npm test
# Lint code
npm run lint
# Format code
npm run format
# Build the .mcpb bundle for Claude Desktop (see section below)
npm run mcpbRunning Locally
# Development mode
npm run dev
# Production mode
npm startTesting with MCP Inspector
Use the MCP Inspector to test tools during development:
npx @modelcontextprotocol/inspector node dist/index.jsThen open http://localhost:5173 in your browser.
Building the .mcpb bundle (Claude Desktop release)
The .mcpb archive is what users double-click to install in Claude Desktop. The installer reads manifest.json#user_config and shows a credential prompt โ no JSON editing or env-var fiddling.
# Prerequisites: mcpb CLI (one-time)
npm install -g @anthropic-ai/mcpb
# Build the bundle
npm run mcpbThis runs scripts/build-mcpb.sh, which:
Runs the full quality pipeline (
npm run buildโ lint โ format โ test โ tsc).Stages a clean tree in a temp directory (only
dist/,manifest.json,package.json,LICENSE,README.md,icon.pngif present).Runs
npm ci --omit=devinside staging โ dev deps (typescript, eslint, vitest) never enter the bundle.@testingbot/automation-mcpis pulled from npm at the version pinned inpackage.json.Validates the manifest and runs
mcpb packhonoring.mcpbignore(strips test fixtures, source maps, dependency changelogs).Writes
releases/testingbot-mcp-server-<version>.mcpband runsmcpb infoon it.
Output is roughly 160 MB โ most of that is the bundled appium-mcp mobile driver stack (XCUITest, UiAutomator2). The bundle is paid for once at install, not at runtime.
Sibling repo during development
For active development on both @testingbot/mcp-server and @testingbot/automation-mcp in lockstep, use npm run dev:rebuild from this repo. It builds both, then npm links the sibling into this repo's node_modules so edits in ../testingbot-automation-mcp/src/ take effect on the next rebuild without a republish.
The link is one-shot โ once set up, dev:rebuild notices it's in place and just builds. If you ever run npm install in this repo, the link is replaced with the registry copy; rerun dev:rebuild to restore.
Releasing
The release flow has two coordinated publish steps:
Publish
@testingbot/automation-mcpto npm (from../testingbot-automation-mcp):npm version patch # or minor / major npm publish # publishConfig.access is "public" โ handles scoped-pkg defaultsBump this repo to consume the new automation-mcp and cut a release:
npm install @testingbot/automation-mcp@latest # updates package-lock.json npm version patch # also syncs manifest.json + server.json git push --follow-tags # โ Create a GitHub release at the new tag. The Build MCPB workflow # fires on release:published and attaches releases/*.mcpb to it.
The release CI (.github/workflows/build-mcpb.yml) runs npm run mcpb on macos-latest and uploads the bundle as both a workflow artifact (30-day retention) and a release asset. Manual re-build: trigger via the Actions tab โ "Build MCPB bundle" โ enter the tag.
macOS is chosen so the bundled appium-xcuitest-driver carries its native bits. If you only target Linux/Windows users, you can switch the runner to ubuntu-latest for ~10ร cheaper minutes โ at the cost of iOS support in the bundled mobile path. Browser tools (via WebDriver) work cross-platform regardless.
To validate the manifest without building:
npm run mcpb:validateTo inspect a built bundle:
mcpb info releases/testingbot-mcp-server-<version>.mcpb
mcpb unpack releases/testingbot-mcp-server-<version>.mcpb /tmp/unpacked # see what's insideThe bundle is unsigned. To sign for distribution, run mcpb sign --self-signed (smoke-test) or mcpb sign with a real cert. See mcpb sign --help.
releases/*.mcpb is gitignored โ upload the artefact to the GitHub releases page (or wherever your install URL points at) after building.
Project Structure
testingbot-mcp-server/
โโโ src/
โ โโโ index.ts # Entry point
โ โโโ server-factory.ts # MCP server setup
โ โโโ config.ts # Configuration management
โ โโโ lib/
โ โ โโโ types.ts # TypeScript types
โ โ โโโ constants.ts # Constants and enums
โ โ โโโ error.ts # Error classes
โ โ โโโ logger.ts # Logging setup
โ โ โโโ utils.ts # Utility functions
โ โ โโโ get-auth.ts # Authentication helpers
โ โ โโโ app-automate-client.ts # REST client for Maestro/Espresso/XCUITest
โ โโโ tools/
โ โโโ maestro.ts # Maestro run tools (upload, run, poll, diagnose)
โ โโโ app-automate.ts # Espresso & XCUITest run tools
โ โโโ browsers.ts # Browser & device tools
โ โโโ tests.ts # Test management tools
โ โโโ builds.ts # Build management tools
โ โโโ storage.ts # Storage tools
โ โโโ screenshots.ts # Screenshot tools
โ โโโ user.ts # User management tools
โ โโโ team.ts # Team management tools
โ โโโ cdp.ts # Chrome DevTools Protocol tools
โ โโโ tunnels.ts # Tunnel management tools
โ โโโ live.ts # Live testing session tools
โโโ tests/
โ โโโ tools/ # Unit tests
โโโ dist/ # Compiled output
โโโ package.jsonTroubleshooting
Authentication Errors
If you see authentication errors:
Run the
tb_logintool (just ask the agent to "log me in to TestingBot") โ the simplest fix, no key/secret neededOr verify your credentials at https://testingbot.com/members/user/security
Ensure environment variables are set correctly (env vars override the
tb_logincredentials file)Check that there are no extra spaces in your credentials
Connection Issues
If the MCP server won't connect:
Restart your MCP client (Claude Desktop, VS Code, etc.)
Check the MCP client logs for errors
Verify Node.js version is >= 20
Tool Execution Errors
If tools fail to execute:
Check the server logs for detailed error messages
Verify you have sufficient permissions/quota in your TestingBot account
Ensure all required parameters are provided
Debug Logging
To enable debug logging, set the LOG_LEVEL environment variable:
export LOG_LEVEL=debugOr in your MCP client configuration:
{
"mcpServers": {
"testingbot": {
"command": "npx",
"args": ["-y", "@testingbot/mcp-server"],
"env": {
"TESTINGBOT_KEY": "your-api-key",
"TESTINGBOT_SECRET": "your-api-secret",
"LOG_LEVEL": "debug"
}
}
}
}Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
Fork the repository
Create your feature branch (
git checkout -b feature/amazing-feature)Commit your changes (
git commit -m 'Add some amazing feature')Push to the branch (
git push origin feature/amazing-feature)Open a Pull Request
License
This project is licensed under the MIT License - see the LICENSE file for details.
Support
๐ง Email: support@testingbot.com
๐ Issues: GitHub Issues
๐ Documentation: TestingBot MCP Documentation
Related
Available Tools
73 toolsanalyzeTestFailureA
Explain why a test failed with TestingBot AI Insights. Starts an AI failure analysis of a finished test (or returns the existing one without extra cost) and waits for the result. The test's curated, secret-masked logs are sent to TestingBot's AI provider, so this requires the account owner to have enabled AI Analysis in Account Settings. Use getFailureLogs instead when you want the raw logs.
Inputs: sessionId (required), force, waitSeconds.
cancelMaestroRunC
Cancel a running Maestro run.
Inputs: runId (required), projectId (required).
createCdpSessionA
Create a remote browser session on TestingBot and get its CDP (Chrome DevTools Protocol) URL for direct browser control. Use this to automate browsers via CDP clients like Puppeteer or Playwright.
Inputs: platform (required), browserName (required), name, build, +4 more.
deleteBuildB
Delete a build and all its associated tests by build ID.
Inputs: buildId (required).
deleteStorageFileC
Delete a file from TestingBot storage using its app_url.
Inputs: appUrl (required).
deleteTestB
Delete a test by session ID. This permanently removes the test and its associated data.
Inputs: sessionId (required).
deleteTunnelB
Delete an active TestingBot tunnel by its ID. This will terminate the tunnel connection.
Inputs: tunnelId (required).
explainVisualRunA
Explain what changed in a visual run: each changed region with what it is, an AI description of the change when the account has AI region names on, text and CSS changes from the page, plus links to the screenshot, baseline and diff images. Read-only.
Inputs: runId (required).
getAccessibilityFindingsA
Read the findings of an accessibility scan: failing WCAG A/AA rules with the elements (CSS selector, HTML, how to fix), checks that need human review, best-practice recommendations, and what is new or resolved since the previous scan.
Inputs: runId (required), elementsPerRule.
getAccessibilityRunsA
List the scans of one accessibility test, newest first, with score and issue counts.
Inputs: testId (required), limit, offset.
getAccessibilityTestsB
List the account's scheduled accessibility tests (each scans one URL) with their latest result.
Inputs: limit, offset.
getAiFailureAnalysisA
Read the AI failure analysis (TestingBot AI Insights) of a test: summary, root cause, timeline, log evidence, suggested fixes, failure category, likely owner and confidence. Read-only: never starts an analysis or sends data to the AI provider. Requires the account owner to have enabled AI Analysis.
Inputs: sessionId (required).
getAppAutomateRunResultsB
Get the results of a completed Espresso/XCUITest project: per-run outcomes plus the JUnit XML report. For XCUITest, pass runId for a single run's report.
Inputs: framework (required), projectId (required), runId.
getAppAutomateRunStatusA
Get the status of Espresso/XCUITest run(s) for a project. Omit runId to list all runs. Statuses: WAITING, READY (running), DONE, FAILED.
Inputs: framework (required), projectId (required), runId.
getBrowsersB
Get list of available browsers and platforms for testing. Optionally filter by type (web or mobile).
Inputs: type.
getBuildsB
Get a list of builds with optional pagination. Builds group related tests together.
Inputs: limit, offset.
getDevicesB
Get list of available mobile devices for testing (real devices and simulators).
Inputs: no named parameters.
getFailureLogsA
Fetch and return session log file content (selenium, browser, chrome, vm, appium) for a test by session ID. Use this to debug failures โ pass failuresOnly=true to extract only error/exception/stack-trace lines.
Inputs: sessionId (required), logTypes, timeoutMs, failuresOnly, +1 more.
getMaestroFlowDetailsA
Get the detailed result of a single Maestro flow: error messages, step-level JUnit report, and links to the video, screenshots, and device logs. Use this to diagnose why a flow failed before fixing it and calling retryMaestroRun.
Inputs: runId (required), flowId (required), projectId (required).
getMaestroRunResultsA
Get the final results of a completed Maestro run: per-flow outcomes (failures first, with error messages and video links) plus the JUnit XML report.
Inputs: runId (required), projectId (required).
getMaestroRunStatusA
Get the status of Maestro run(s) for a project. Omit runId to list all runs of the latest execution. Statuses: WAITING, READY (running), DONE, FAILED, CANCELLED.
Inputs: projectId (required), runId.
getScreenshotListB
Get a list of all screenshot jobs with pagination.
Inputs: limit, offset.
getStorageFilesC
List all files in TestingBot storage with pagination.
Inputs: limit, offset.
getTeamA
Retrieve team settings: plan details, team size, and concurrency (parallel sessions allowed, running now, and queued waiting for a free slot, for VMs and physical devices). Check this before starting many sessions in parallel.
Inputs: no named parameters.
getTestDetailsA
Get detailed information about a specific test by session ID. Includes logs, screenshots, video URLs, and execution metadata.
Inputs: sessionId (required).
getTestsA
Retrieve a list of recent tests with optional pagination. Returns test details including status, browser, platform, video and duration.
Inputs: limit, offset.
getTestsForBuildB
Get all tests associated with a specific build ID.
Inputs: buildId (required).
getTunnelListA
Get a list of all active TestingBot tunnels on the account, with their identifiers. Tunnels allow you to test websites behind firewalls or on your local machine.
Inputs: no named parameters.
getUserFromTeamC
Retrieve detailed information about a specific user in your team by their user ID.
Inputs: userId (required).
getUserInfoA
Get current user account information including minutes used, plan details, and account status.
Inputs: no named parameters.
getUsersInTeamA
Get a list of all users in your team with their roles and permissions.
Inputs: no named parameters.
getVisualRunsA
List visual runs (one browser's screenshot compared with its baseline), newest first. Use state=unreviewed to find failed runs nobody has rejected yet.
Inputs: limit, state, offset, testId.
getVisualTestsB
List the account's hosted visual regression tests (id, name, URL, browsers, paused).
Inputs: limit, offset.
listMaestroProjectsA
List Maestro projects on the account (newest first): app details, flow names, and run IDs. Use this to find an existing projectId instead of re-uploading an app.
Inputs: count, offset.
listMaestroRunsA
List Maestro runs across all projects (newest first), or look up runs by their build/run name. Returns projectId + runId pairs for use with getMaestroRunStatus and getMaestroRunResults.
Inputs: count, offset, buildName.
listTestFilesB
Scan a project directory and return test files for the detected framework. Read-only โ never modifies files.
Inputs: projectRoot (required), maxDepth, maxResults.
maestroCheatSheetA
Get a Maestro flow YAML syntax reference: file structure, commands, selectors, and the TestingBot run workflow. Call this before writing or fixing Maestro flows.
Inputs: no named parameters.
retrieveScreenshotsA
Retrieve screenshot results by screenshot ID. Returns URLs to the generated screenshots.
Inputs: screenshotId (required).
retryMaestroRunB
Retry a Maestro run, or a single failed flow within it when flowId is given.
Inputs: runId (required), projectId (required), flowId.
reviewVisualRunA
Approve or reject a visual run, the same as on its run page. Approving with makeBaseline=true also makes its screenshot the new baseline for that browser. Only do this when the user asked you to.
Inputs: runId (required), decision (required), makeBaseline.
runAccessibilityTestA
Start a scan of a scheduled accessibility test now (like Run now in the dashboard). Poll getAccessibilityRuns for the new run.
Inputs: testId (required).
runAppAutomateTestA
Start an Espresso or XCUITest run on a TestingBot device. Returns immediately with the run ID โ it does NOT wait for completion. Poll with getAppAutomateRunStatus, then fetch getAppAutomateRunResults. If the app needs a localhost / private-network backend, start a tunnel first (startTunnel): the run uses the account's newest running tunnel. On Android, point the app at a hostname that resolves to 127.0.0.1 on the tunnel's machine (e.g. myapp.localtest.me), not localhost, which Android never proxies.
Inputs: framework (required), projectId (required), name, build, +10 more.
runMaestroTestA
Start a Maestro test run on a TestingBot device. Returns immediately with the run ID โ it does NOT wait for completion. Poll with getMaestroRunStatus, then fetch getMaestroRunResults once completed.
Inputs: projectId (required), platformName (required), env, name, +8 more.
setupTestingBotA
Detect the testing framework in a project and return the ready-to-paste TestingBot configuration snippet, install command, and env-var requirements. Read-only โ never modifies files; the agent or user applies the snippet.
Inputs: projectRoot (required), frameworkOverride.
startDesktopLiveSessionB
Convenience tool to start a desktop browser live testing session. Automatically sets platformType to 'desktop'. For localhost / private-network URLs, pass the tunnelId of a running tunnel (startTunnel).
Inputs: desiredOS (required), desiredURL (required), desiredBrowser (required), desiredOSVersion (required), +2 more.
startLiveSessionA
Start an interactive live testing session on TestingBot. Returns a link that opens the session in the user's TestingBot dashboard (they confirm with Start). Supports desktop browsers (Chrome, Firefox, Safari, Edge, IE) and mobile emulators/simulators (Android, iOS). For localhost / private-network URLs, start a tunnel first (startTunnel) and pass its numeric ID as tunnelId.
Inputs: desiredOS (required), desiredURL (required), platformType (required), desiredOSVersion (required), +4 more.
startMobileLiveSessionB
Convenience tool to start a live testing session on a mobile emulator/simulator. Automatically sets platformType to 'mobile'. For localhost / private-network URLs, pass the tunnelId of a running tunnel (startTunnel).
Inputs: desiredOS (required), desiredURL (required), desiredDevice (required), desiredOSVersion (required), +1 more.
startTunnelA
Start a TestingBot Tunnel on this machine so remote browsers and devices can reach localhost, private-network and intranet URLs. Call this BEFORE testing any local or private URL. Waits until the tunnel is ready (can take up to a minute on first use, which downloads the tunnel) and returns its identifier โ pass that as tunnelIdentifier to tb_openBrowser / runMaestroTest. Requires Java 17+ on this machine. The tunnel keeps running until stopTunnel is called or the MCP server exits.
Inputs: noBump, shared, noCache, tunnelIdentifier.
stopTestB
Stop a running test by session ID. This terminates the test execution immediately.
Inputs: sessionId (required).
stopTunnelA
Stop a TestingBot Tunnel that was started with startTunnel. Without a tunnelIdentifier, stops the only one running (or all of them with all: true). For tunnels started outside this MCP server, use deleteTunnel.
Inputs: all, tunnelIdentifier.
takeScreenshotA
Take screenshots of a URL across multiple browsers and platforms. Returns a screenshot ID to retrieve results. localhost / private-network URLs are captured through the account's newest running TestingBot Tunnel โ start one with startTunnel first.
Inputs: url (required), browsers (required), fullPage, waitTime, +1 more.
tb_clickC
Click an element. Use by to pick a locator strategy (css/xpath/id/name/tag/class/linkText/partialLinkText).
Inputs: value (required), sessionId (required), by, timeoutMs.
tb_closeBrowserA
Close a remote browser session. Releases TestingBot minutes. For mobile device sessions, use appium-mcp's appium_session_management with action: 'delete'.
Inputs: sessionId (required).
tb_executeScriptB
Execute a JavaScript snippet in the active page and return its result. The script body is wrapped as a function โ use return to send a value back. Args are passed positionally via arguments[0], arguments[1], ...
Inputs: script (required), sessionId (required), args.
tb_getAttributeB
Read an attribute of an element (e.g. 'href', 'value', 'aria-label', 'class', 'data-*').
Inputs: value (required), attribute (required), sessionId (required), by, +1 more.
tb_getTextA
Read the visible text of an element. Cheaper than tb_snapshot when you just need to verify a single label / status.
Inputs: value (required), sessionId (required), by, timeoutMs.
tb_listSessionsA
List all active browser sessions managed by this server. Useful when you've lost track of a sessionId. (Mobile device sessions are NOT listed here โ they live inside appium-mcp; use appium_session_management with action 'list'.)
Inputs: no named parameters.
tb_loginA
Authenticate with TestingBot โ no API key or secret to copy or paste. By default it opens your browser, you click Authorize, and the credentials are captured automatically and saved to ~/.testingbot/credentials (used by every later tool call this session โ no restart). If your browser can't reach this machine (SSH / remote / dev container / web), it falls back to a short URL + code you enter in any browser; pass mode:"device" to force that. After authorizing in the browser, call tb_login again to finish. Call this whenever credentials are missing.
Inputs: mode.
tb_openBrowserA
Start a remote browser session on TestingBot via WebDriver. Handles BOTH desktop browsers (Chrome/Edge/Safari/Firefox on Win/macOS/Linux) AND mobile browsers (Chrome on Android, Safari on iOS). For a mobile browser task, set deviceName and platformVersion โ the session is still WebDriver/chromedriver-backed, so tb_navigate / tb_snapshot / tb_screenshot / tb_click work directly with no native-context juggling. By default a mobile session runs on an EMULATOR (Android) / SIMULATOR (iOS); set realDevice: true to run on a physical device instead โ ALWAYS do this when the user asks for a 'real device', 'physical device', or 'real hardware'. Prefer this over appium_session_management for any task whose goal is loading a web page in a browser, even on mobile. Reserve appium_session_management for native-app testing (.apk/.ipa). Local or private sites (localhost, 127.0.0.1, 10.x/192.168.x, intranet hosts): the remote browser can only reach these through a running TestingBot Tunnel, and only when this session names that tunnel via tunnelIdentifier โ without it the session silently goes direct and the page fails to load. Returns a sessionId for subsequent tool calls and a liveViewUrl the human can open to watch the agent drive in real time. Burns TestingBot minutes โ call tb_closeBrowser when done.
Inputs: platform (required), browserName (required), name, build, +7 more.
tb_pressKeyA
Press a key (or chord) on the active browser session. Uses W3C key names: 'Enter', 'Tab', 'Escape', 'Control+A', 'Meta+Shift+Z', etc. Sent to the currently-focused element.
Inputs: key (required), sessionId (required).
tb_screenshotA
Capture a PNG screenshot of the active browser session. Returns a base64 image content block AND saves the PNG to disk, returning a clickable file:// link โ many MCP clients (e.g. Claude Desktop) don't render tool-returned images inline, so the saved file is the reliable way for a human to view it. Pass savePath to control where it's written (a .png file path, or a directory); otherwise it goes to the OS temp dir.
Inputs: sessionId (required), savePath.
tb_snapshotA
Return a structured snapshot of the current page: title, URL, headings, links/buttons with their text, and a truncated body. Use this as the agent's 'see the page' primitive before deciding what to click.
Inputs: sessionId (required), bodyChars.
tb_typeA
Type text into an input. Uses the same locator strategies as tb_click. Clears the field first by default.
Inputs: text (required), value (required), sessionId (required), by, +2 more.
updateTestB
Update test metadata such as name, status (passed/failed), and other attributes. Useful for marking tests after execution.
Inputs: sessionId (required), name, build, extra, +1 more.
updateUserInfoC
Update user account information such as name, email, or other profile details.
Inputs: email, lastName, firstName.
uploadAppAutomateAppA
Upload the app under test for an Espresso (.apk/.aab) or XCUITest (.ipa) run on TestingBot. Returns a projectId for uploadAppAutomateTests and runAppAutomateTest. For Maestro flows use uploadMaestroApp instead.
Inputs: framework (required), localFilePath (required).
uploadAppAutomateTestsB
Upload the test suite for an App Automate project: the instrumented test APK for Espresso, or the zipped XCUITest runner bundle for XCUITest.
Inputs: framework (required), projectId (required), localFilePath (required).
uploadFileA
Upload a local file (APK, IPA, or ZIP) to TestingBot storage for mobile app testing. Returns an app_url for use in tests.
Inputs: localFilePath (required).
uploadMaestroAppA
Upload a mobile app (APK, AAB, IPA, or zipped .app) for Maestro testing on TestingBot. Skips the upload if the same binary was uploaded before. Returns a projectId used by uploadMaestroFlows and runMaestroTest.
Inputs: localFilePath (required).
uploadMaestroCompanionAppA
Upload a companion app (.apk/.aab/.ipa) that should be installed alongside the app under test in a Maestro run. Returns a tb:// app URL to pass in runMaestroTest's otherApps parameter (max 4 per run).
Inputs: localFilePath (required).
uploadMaestroFlowsA
Upload Maestro flow YAML files for a project. Accepts a local directory (all .yaml/.yml files, preserving structure), a pre-built .zip, or inline flow content. Replaces any previously uploaded flows for the project.
Inputs: projectId (required), flows, flowsPath.
uploadRemoteFileC
Upload a file from a remote URL to TestingBot storage. The file will be downloaded from the URL and stored.
Inputs: remoteUrl (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogโฆ
TDQS
Scored across 73 tools
Most tools target distinct resources or workflows, and descriptions often clarify family-specific tools (Maestro vs App Automate vs visual vs accessibility). However, there is notable overlap among session-start tools (startLiveSession, startDesktopLiveSession, startMobileLiveSession, tb_openBrowser, createCdpSession), tunnel cleanup tools (stopTunnel vs deleteTunnel), and screenshot-related tools. The large surface makes boundary decisions harder even when each description is informative.
Many tools follow a camelCase verb-noun convention, but the set mixes unprefixed camelCase names, a tb_ snake_case-prefixed browser-control family, and noun-style names like maestroCheatSheet. The tb_ grouping is deliberate and readable, but overall naming is not uniform across the server.
At 73 tools, the server is far beyond the typical 3-15 well-scoped range and is heavy even for a broad testing platform. Several tools are convenience wrappers or narrow variants, which adds surface area without proportional independent capability.
The server covers many TestingBot workflows: sessions, tunnels, storage, tests/builds, Maestro, App Automate, accessibility, visual regression, account, and team. Still, several subdomains lack full lifecycle coverage, such as create/update/delete for accessibility and visual tests, cancelling App Automate runs, and deleting Maestro projects. These are notable gaps but agents can often work around them through the dashboard or existing tools.
Maintenance
Related MCP Connectors
Run, debug, and triage tests from your IDE using natural language, no dashboard switching, no manual data transfers. The TestMu AI (formerly LambdaTest) MCP Server is a single remote server exposing four tool suites: HyperExecute โ analyze your project, generate YAML configs and test runner commands, then monitor jobs and sessions. Automation โ pull a TestID's details plus command, network, and console logs into one chat for instant root-cause analysis. Includes mobile app upload. SmartUI โ explain pixel, layout, DOM, and perceptual changes in a visual regression run, with context-aware React/HTML/CSS fixes. Accessibility โ audit any public URL or a local React app against WCAG and get ready-to-apply remediation steps. Connects over https://mcp.lambdatest.com/mcp using OAuth 2.1 โ no API keys in your config. One-click install in Cursor; works with Claude, GitHub Copilot, Cline, and any MCP client. Tests execute on the TestMu AI cloud: 3,000+ browsers and 10,000+ real devices.
Official MCP server for Qase โ manage test cases, runs, suites, defects via AI tools.
Official Browserless MCP server: browser automation, scraping, screenshots and PDFs for AI agents.
MCP server for building and testing AI agents with multi-model experimentation and insights.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP serverr for Lastest to manage your tests, AI create them, run them, and speed up AI-development.22Functional Source , Version 1.1, ALv2 Future
- FlicenseNot gradedqualityDmaintenanceMCP server for the Argus E2E Testing Agent, enabling AI coding assistants to perform browser testing, quality intelligence, CI/CD integration, discovery, time travel debugging, visual AI testing, correlation analytics, and API testing directly from the IDE.-
- FlicenseNot gradedqualityDmaintenanceMCP server that enables AI agents to automate browser testing via Chromium, providing tools for navigation, interaction, and inspection.-
- AlicenseNot gradedqualityDmaintenanceA universal AI-powered testing server built on the Model Context Protocol (MCP). Allows AI agents to inspect, execute, test, monitor, debug, and report on software projects.3GNU Lesser General Public v2.1 only