- Clickcast @alexkay28/clickcastDrive a real Playwright browser: annotated screenshot + structured page state after every action.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- QualityMax QA MCP @quality-max/qmax-mcpLocal QA MCP: scan URLs, inspect pages, generate Playwright repros, and run tests.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Test Intel @barissozudogru/test-intelCoverage analysis, untested function detection and complexity scoring for TS and JS.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- GridProof @gridproof/gridproofGridproof your UI — automated spacing & grid QA in the agent loop (MCP server).4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- five46 @sekharsdet/five46BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Testa @valewnrt/testaDrive the iOS Simulator from an agent: read the screen, tap/type/swipe, replay flows in CI.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- TestAtlas @karzone/testatlas-mcpSemantic map of a .NET test-automation solution for AI agents — search, impact, endpoints2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.3 GitHub stars.
- Reelier @seldonframe/reelierSnapshot tests and CI for agent workflows: record a run, replay it at 0 tokens, diff for drift.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- ariadne @mikhailhal/ariadneReturns only the unit tests affected by your current Kotlin/Android code changes.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Browserbash @pramoddutta/browserbashPlain-English browser tests for AI agents: real Chrome, deterministic verdicts. Free, no API keys.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Sendblue Browser @sendblue-api/sendblue-browser-mcpDrive a stealth-patched Chromium daemon: navigate, screenshot, eval JS, attach over CDP.21% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Allure TestOps @mshegolev/allure-testops-mcpAllure TestOps MCP — projects, launches, test cases, test results via REST API.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- RokuMCP @jack1590/rokumcpMCP server for Roku device automation — deploy, ECP control, screenshots, and debug console5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Tripwire @aliboily/tripwireMCP for Roblox Studio and Open Cloud: drive Studio, run headless tests, and review game security.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- SpecLeft @specleft/specleftPython intent tracing MCP: map specs to pytest tests, monitor implementation progress, offline-only.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.3 GitHub stars.
- React Toolkit @nishant-chaudhary5338/mcp-react-toolkit9 MCP servers for React/TypeScript — dep auditing, a11y, test gen, and TypeScript enforcement.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.3 GitHub stars.
- Smolanalytics @arjun0606/smolanalyticsEnd-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.3 GitHub stars.
- Jet Browser Verifier @masakaai/jet-browserVerify an isolated WPE WebKit runtime with native-input, DOM, PNG, and cleanup evidence.Not assessed yet.Runs on your machine, installed from Docker.2 GitHub stars.
- Local LLM Worker @joblessjoe/local-llm-workerLocal LLM does Claude's bulk work: reads logs and files, researches the web, writes test-gated code.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- jevnav @dtduc-git/jevnavReplayable browser automation: Jev picks the element, a gate blocks risky actions, every run traces.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- SimMirror @andrewkochulab/sim-mirrorMirror and drive iOS Simulators and iPhones: token-efficient UI snapshots, a live viewer, recording.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- kwin-mcp @vibeprogramm/kwin-mcpKDE Plasma 6 Wayland GUI automation for AI agents: 30 tools (EIS input, screenshots, AT-SPI2).9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- ResiliReplay @aliengineering-byte/resilireplayRun bounded, deterministic MCP reliability tests and generate executable regressions.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Verdict QA @artjack/verdictRead-only MCP server over Verdict QA state: verdicts, findings, flaky quarantine, history.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
