TestMu AI (formerly LambdaTest)
io.github.LambdaTest/mcp · v1.0.7 · score 89/100 · checked 2026-11-22
Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works
Agentic AI quality engineering: run, debug and triage tests on real browsers and devices
Source: https://github.com/LambdaTest/mcp-server-guide
Findings
| Severity | Rule | Detail |
|---|---|---|
| Low | MW005 | Remote endpoint lists 88 tool(s) to anyone, no credentials needed. |
| Medium | MW102 | 18 tool(s) can execute commands or delete data (generateHyperExecuteYAML, answerHyperExecuteQuery, getHyperExecuteJobInfo, getHyperExecuteJobSessions, deleteBuild and 13 more). Require confirmation before the agent calls them. |
What was checked
- https://mcp.lambdatest.com/mcp: answers without auth
Public tools: upload_app, generateHyperExecuteYAML, answerHyperExecuteQuery, getHyperExecuteJobInfo, getHyperExecuteJobSessions, getAccessibilityReport, analyzeAppViaTunnel, buildLocalAppForAnalysis, getAutomationTestDetails, getAutomationTestCommandLogs, getAutomationTestNetworkLogs, getAutomationTestBrowserConsoleLogs, getAutomationTestSeleniumLogs, automationQuery, updateBuild, stopBuild, deleteBuild, triggerSuiteRun, getSuiteOverview, getSupportedPlatforms, listTunnels, stopTunnel, deleteSession, updateSession, stopSession, getSessionScreenshots, getSessionVideo, getSessionV2CommandLogs, getSessionV2SeleniumLogs, postSessionExceptions
Maintainer? Add the badge
Grades refresh daily. Think a finding is wrong? Dispute this grade.
[](https://www.mcpwatch.io/s/io-github-lambdatest-mcp-a39ba489)