TestMu AI MCP Server
TestMu AI MCP Server: запуск и разбор тестов на LambdaTest прямо из IDE
От сообщества: Добавлен пользователем или импортирован; проверьте владельца перед подключениемРаботаетБез входаГлобальныйБесплатноТолько чтение
Что умеет
- Загружать приложения для мобильного тестирования
- Генерировать YAML-конфигурацию для HyperExecute
- Разбирать логи и падения тестов автоматизации
- Анализировать визуальные различия SmartUI
- Получать отчёты по доступности (a11y)
Какие данные видит
Ассистент работает от имени аккаунта LambdaTest через OAuth и видит только тесты и отчёты этого аккаунта.
Нужен ли аккаунт
Не нужен: сервер работает без входа
TestMu AI MCP Server позволяет запускать, отлаживать и разбирать автотесты естественным языком из Cursor, Claude или GitHub Copilot. Сервер работает с HyperExecute, визуальным регрессионным тестированием SmartUI, проверками доступности и логами автоматизации LambdaTest.
Как подключить
Как подключить TestMu AI MCP Server к Claude
Адрес сервера, который нужно вставить в настройках Claude:
https://testmu-mcp--rahulj.run.tools
- Откройте Claude (сайт claude.ai или приложение для компьютера).
- Перейдите в Настройки → Коннекторы (в английском интерфейсе: Settings → Connectors).
- Нажмите Добавить пользовательский коннектор (Add custom connector).
- Вставьте адрес сервера, скопированный ниже, в поле URL удалённого MCP-сервера и нажмите Добавить.
- В чате нажмите + → Коннекторы и включите новый коннектор.
Пользовательские коннекторы доступны на тарифах Free, Pro, Max, Team и Enterprise. На Free можно добавить только один. В Team и Enterprise коннектор сначала добавляет владелец организации в Настройки организации → Коннекторы.
Авторизация
После нажатия Добавить откроется окно входа в сервис. Войдите под своим аккаунтом и подтвердите доступ. Пароль Claude не видит.
Как подключить TestMu AI MCP Server к ChatGPT
Адрес сервера, который нужно вставить в настройках ChatGPT:
https://testmu-mcp--rahulj.run.tools
- Откройте ChatGPT в браузере (chatgpt.com). Нужен тариф Plus, Pro, Business, Enterprise или Edu.
- Один раз включите режим разработчика: Настройки → Приложения → Дополнительные настройки → Режим разработчика (Settings → Apps → Advanced settings → Developer mode).
- Откройте Настройки → Коннекторы и нажмите Создать (Create).
- Заполните форму: Название (любое), Описание (одна фраза, что делает сервис), URL MCP-сервера (скопируйте ниже).
- В поле Аутентификация выберите OAuth, если сервис требует вход, иначе Нет. Нажмите Создать.
- В новом чате откройте + → Приложения/Коннекторы и включите коннектор.
Название раздела у OpenAI менялось (Connectors → Apps/Plugins). Если пункт называется иначе, ищите «режим разработчика» в настройках. В рабочих пространствах Business/Enterprise администратор должен разрешить пользовательские коннекторы.
Авторизация
При первом использовании ChatGPT откроет окно входа в сервис. Войдите и подтвердите доступ.
Как подключить TestMu AI MCP Server к Cursor
Адрес сервера, который нужно вставить в настройках Cursor:
https://testmu-mcp--rahulj.run.tools
Быстрый способ: нажмите кнопку Открыть в Cursor ниже, Cursor сам предложит добавить сервер.
Вручную:
- В Cursor откройте Settings → Cursor Settings → MCP и нажмите Add new global MCP server.
- Вставьте JSON, скопированный ниже, в открывшийся файл
~/.cursor/mcp.json(для одного проекта:.cursor/mcp.jsonв корне проекта). - Сохраните файл. Сервер появится в списке MCP; при необходимости пройдите авторизацию по кнопке рядом с ним.
Авторизация
Если сервис требует вход, рядом с сервером в списке MCP появится кнопка авторизации.
Список инструментов сервера (60)
Технические названия из tools/list. Нужны только разработчикам.
| upload_app | Uploads an app to LambdaTest for mobile testing and displays upload status. |
| generateHyperExecuteYAML | Generates a HyperExecute YAML configuration for running tests on LambdaTest's HyperExecute platform. REQUIRED fields: project (language, framework) and testing (testDiscovery.command, testRunnerCommand) All other fields are OPTIONAL. Supports multiple languages and frameworks: - JavaScript/TypeScript: Playwright, Cypress, WebDriverIO, Puppeteer, Taiko - Python: Pytest, Behave, Robot Framework - Java: TestNG, JUnit, Cucumber - Ruby: RSpec, Capybara - C#: NUnit, xUnit, MSTest - Mobile (ONLY use appTesting for these): XCUI (iOS), Espresso (Android), Appium Features: - Smart framework defaults for common configurations - Input validation with security checks - Caching and artifact upload configuration - Git integration via sourcePayload - Mobile app testing support (via optional appTesting field) NOTE: For web automation (Selenium, Playwright, Cypress, etc.), do NOT include appTesting field. |
| answerHyperExecuteQuery | Answers questions about HyperExecute features, configuration, usage, troubleshooting, and best practices by searching through documentation. |
| getHyperExecuteJobInfo | Fetches and displays information about a HyperExecute job including status, test results, and progress. |
| getHyperExecuteJobSessions | Fetches and displays session information for a HyperExecute job. |
| getAccessibilityReport | Fetches accessibility report for URLs |
| analyzeAppViaTunnel | Analyzes a locally running app for accessibility via LambdaTest tunnel. |
| buildLocalAppForAnalysis | Builds the application from codebase, serves it locally, and analyzes accessibility issues. |
| getSmartUIResources | Gets resources for a SmartUI comparison |
| summarizeSmartUIPixelDiff | Summarizes SmartUI pixel differences |
| summarizeSmartUILayoutDiff | Summarizes SmartUI layout differences |
| summarizeSmartUIDomDiff | Summarizes SmartUI DOM differences |
| analyzeSmartUIHumanDiff | Analyzes SmartUI differences from a human perspective |
| analyzeSmartUIRun | Analyzes a SmartUI test run |
| getAutomationTestDetails | Fetches detailed information about an automation test by ID |
| getAutomationTestCommandLogs | Fetches command logs for a specific automation test |
| getAutomationTestNetworkLogs | Fetches network logs for a specific automation test |
| getAutomationTestBrowserConsoleLogs | Fetches Browser Console logs for a specific automation test. Note: Not available for mobile app automation tests. |
| getAutomationTestSeleniumLogs | Fetches Selenium logs (web), Appium logs (mobile/Appium), or instrumentation logs (mobile/XCUI/Espresso) for a specific automation test. Automatically detects XCUI and Espresso tests and fetches the correct log type. |
| automationQuery | Unified tool for querying LambdaTest automation resources: builds, sessions, tests, and logs. Supports listing builds, getting build details, deleting/updating/stopping builds, listing sessions in a build, fetching test details, and retrieving test logs (command, network, console, selenium, instrumentation). Use logType "instrumentation" for XCUI and Espresso test logs. |
| triggerSuiteRun | Triggers a phone call test run for a specific suite. This will initiate phone calls for all scenarios configured in the suite. |
| getSuiteOverview | Gets comprehensive suite overview for a project including run counts, latest status, scores, schedule information, and active calls. |
| getSupportedPlatforms | Retrieve all supported browser and OS combinations available on LambdaTest (3000+ options). Use this to discover valid values for os, browser, version when setting up test configurations. |
| listTunnels | Retrieve all active LambdaTest tunnel connections for the account. Useful for checking which tunnels are running before starting a new one or debugging local testing connectivity. |
| stopTunnel | Terminate a specific active tunnel connection by tunnel ID. Use this to clean up tunnels that are no longer needed. |
| deleteSession | Permanently delete a specific automation test session from LambdaTest by session ID. |
| updateSession | Update the name or pass/fail status of a test session. Use status_ind to mark tests as passed, failed, error, or skipped from your test framework. |
| stopSession | Stop an active running test session on LambdaTest. |
| getSessionScreenshots | Retrieve command-by-command screenshots captured during a test session. Returns screenshot URLs for each step. |
| getSessionVideo | Retrieve the video recording URL for a completed test session. |
| getSessionV2CommandLogs | Retrieve v2 command execution logs for a test session. Returns structured JSON with enhanced detail compared to v1 logs. |
| getSessionV2SeleniumLogs | Retrieve v2 Selenium/WebDriver grid request and response logs for a test session. |
| postSessionExceptions | Upload exception/error logs from the client machine for a test session. Use this to attach assertion failures or unexpected errors to a session. |
| postSessionAssertions | Upload assertion results for a test session. Use this to attach test assertion outcomes to a session for reporting. |
| postTestExceptions | Upload exception logs for a specific test (by test ID) rather than by session ID. |
| getLiveSessionLogs | Stream live logs from an active test session in real time. |
| getOrgConcurrency | Retrieve the current concurrency usage and limits for the organization on web automation (Selenium/Cypress). |
| getScreenshotTestResult | Retrieve the results and screenshot URLs for a completed or in-progress screenshot test. |
| stopScreenshotTest | Stop an active screenshot test before it completes. |
| getAnalyticsData | Retrieve analytics and test metrics data for the organization including build counts, pass/fail rates, and usage statistics. |
| getFlakyTests | Retrieve a list of flaky tests — tests that pass and fail intermittently — to help identify unstable test cases. (UNDOCUMENTED - may change without notice) |
| getTestTrends | Retrieve test execution trends over time including pass rates, failure rates, and execution counts. (UNDOCUMENTED - may change without notice) |
| getAnalyticsErrors | Retrieve aggregated error data and failure analysis across test sessions. (UNDOCUMENTED - may change without notice) |
| getPerformanceTestResult | Retrieve the results of a completed performance test including Core Web Vitals, load times, and performance scores. |
| uploadPrerunFile | Upload a prerun script or file to LambdaTest. Prerun files execute before the test starts on the remote machine. |
| deletePrerunFile | Delete an uploaded prerun file by stored LambdaTest file path. |
| uploadUserFile | Upload a user file to LambdaTest storage. User files can be referenced in test scripts during execution. |
| deleteUserFile | Delete an uploaded user file by stored LambdaTest file path. |
| listUploadedApps | Retrieve all apps uploaded to LambdaTest for mobile testing. Use type=android/ios for real devices, emulator/simulator for virtual devices. |
| deleteUploadedApps | Delete one or more uploaded apps from LambdaTest by their app IDs. |
| uploadAppVirtualDevice | Upload an app (APK for emulator, IPA for simulator) to LambdaTest for virtual device (emulator/simulator) testing. |
| listDevicesForTesting | Retrieve all available real devices on LambdaTest for mobile app testing. Filter by region and OS. |
| getMobileCapabilityGenerator | Retrieve capability generation data for mobile automation test configuration. |
| listMobileBuilds | Retrieve all mobile automation builds from the LambdaTest mobile automation API. |
| listMobileSessions | Retrieve all mobile automation sessions from the LambdaTest mobile automation API. |
| getMobileConcurrency | Retrieve the current concurrency usage and limits for mobile automation (real device testing). |
| checkAppProcessingStatus | Check whether an uploaded app has been processed and is ready for features like image injection, network logs, and screenshot unblock on real devices. |
| checkAppProcessingStatusVirtualDevice | Check whether an uploaded app has been processed for feature support on virtual devices (emulator/simulator). |
| tm_list_projects | List all Test Manager projects the authenticated user is allowed to see. Supports keyword search and pagination. |
| tm_get_test_cases | Find test cases in a project by filters (folder, priority, automation status, type, tags) and/or search (matches test case ID like TC-123, or title; minimum 3 characters) — returns summaries. Filters combine (AND). Pass case_id instead to get one case's full detail (steps, BDD scenarios, field values). |