- LLM Preflight @feronovak/llm-preflightLocal, cross-provider preflight checks for LLM integration changes.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Dsh Verify @263311487-ux/dsh-verifyAgent-built web app quality gate. Real browser is the judge. PASS/FAIL with receipts.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- CodeSampleX @r2cuerdame/codesamplexCompatibility evidence from real builds: does this library API work on your versions and runtime?5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- Memtrust @rudrendupaul/memtrustIndependent, reproducible benchmark harness for agent-memory backends.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Kāhea @copyleftdev/kaheaDeterministic HTTP/WebSocket testing and policy-gated API execution for AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.2 GitHub stars.
- UI Debugger @developerz-ai/ui-debugger-mcpAutonomous UI debugging MCP server: an agent drives the browser/desktop, reports bugs + UX issues.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- ellmos Blender Use @ellmos-ai/ellmos-blender-use-mcpHeadless Blender asset QA over MCP: background script runs and FBX reimport verification.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Tapp @aarwitz/tappTest iOS, Android, and web apps with agent exploration, replayable flows, and CI gates.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Extentos MCP @extentos/mcp-serverBuild smart-glasses apps with AI agents: scaffold, validate, and simulate before real hardware.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Argus Testing — Autonomous QA MCP @chriswu727/argusAutonomous QA MCP for web and macOS that tests like a real engineer, finds bugs, and verifies them.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Hashloom @davet47/hashloomContent-addressed contracts and a verification cache that cut agent context by skipping proven code.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Hotato @attenlabs/hotatoOpen-source, self-hosted conversation QA for voice agents. MIT.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- Devloop @vincentvella/devloopBrowser + dev-server logs on one correlated timeline, for Claude Code and AI agents.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- WpfPilot MCP @skuzadev/wpfpilot-mcpAutomate Windows WPF apps from AI agents with semantic UIA selectors and FlaUI test generation.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Prufa @prufa-dev/prufa-mcpThe full Prufa QA agent over MCP: audits, flows, monitors, gremlin chaos, discovery.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- MailDev @pierre3/maildev-mcpMailDev MCP server. Manage Docker containers and inspect emails from your AI editor or MCP client.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.2 GitHub stars.
- Heddle @davet47/heddleContent-addressed contracts and a verification cache that cut agent context by skipping proven code.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.2 GitHub stars.
- MCP Compliance @yawlabs/mcp-complianceCLI tool and MCP server that tests MCP servers for spec compliance2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Probe @incultnitollc/mcp-probeInspect and score any MCP server 0-100 on publishability, schema and protocol before publish.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- Baton @kanumuri9593/batonRun, hot-reload and screenshot Flutter, web, React Native and native iOS/Android apps.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Craftwire @uxplima/craftwireSee and drive Minecraft: Fabric client, Paper server, bots, plugin tests, profiling.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Testers.ai CARBON Test Harness Lite @jarbon/carbon-liteLocal QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.Not assessed yet.Runs on your machine, installed from MCPB.1 GitHub stars.
- Groundwork @nickjlamb/groundworkDeployment-readiness checks for document-QA and extraction AI: grounding, extraction, CI gate.Not assessed yet.Runs on your machine, installed from npm.1 GitHub stars.
- Tester @ryudi84/api-testerMCP server for API testing: HTTP requests, cURL generation, health checks.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
