- isitdone @raimondasl/isitdoneMake a coding agent prove it: run the repo's real tests, typecheck and lint before it says done.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- tmodloader-mcp @musharna/tmodloader-mcpDrive a running tModLoader (Terraria) instance from an agent: launch, query, screenshot, read state.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- DelphiCodeCoverage @avelsys/delphi-codecoverageGuide + snippets for Delphi/DUnitX projects that work with the DelphiCodeCoverage tool.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- FIXSIM @gammathreetrading/fixsimTest FIX from Claude, ChatGPT, or Cursor: free sandbox FIX sessions or your own FIXSIM instances.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Cornea, deterministic visual inspection @abduljabbarbxr/corneaDeterministic visual inspection for AI agents. Overlap, overflow, contrast, quality.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from cargo.1 GitHub stars.
- ios-agent @emazaheri/ios-agentDrive a real iPhone or an iOS Simulator with an AI agent, through XCUIAutomation.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Failure Lab @anilloutombam/mcp-failure-labA chaos-engineering and resilience-testing toolkit for Model Context Protocol servers.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Solvegate @solvegate/solvegate-mcpInspect a page for Cloudflare Turnstile free, and clear Turnstile and WAF challenges.23% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- INVARA @jujitae/invaraIndependent verification that a change kept its declared constraints. No model in the verdict path.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- WCAG accessibility @aditya-ariosity/wcag-accessibilityA WCAG accessibility testing MCP for AI agents, Codex, Claude Code, and automated UI audits.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- RuleDrift @ri7in/rule-driftTest whether AI agents retain critical instructions as conversations grow.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tailscale Compute @dylantirandaz/tailscale-computeRun builds, tests, and benchmarks on your own Tailscale compute node.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Evolveguard @rudrendupaul/evolveguardWraps the evolveguard CLI as a single generic MCP tool for agent-skill file safety checks.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Gaffer @gaffer/mcpTest analytics for AI agents: test history, flaky tests, failure clusters, coverage.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- EdgeGate @frozo-ai/edgegate-mcpRegression-test AI models on real Snapdragon and Jetson hardware, with signed evidence for CI.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- PNTR @pntr/pntrFree developer subdomains with DNS, catch-all email, and webhook capture, managed via MCP.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- regressGuard @bharath-code/regressguardDeterministic API regression checks for AI agents: snapshot a baseline, catch broken contracts.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.1 GitHub stars.
- Evidrift @bm1016bm-svg/evidriftCatch TypeScript API and OpenAPI contract drift in AI-generated code, then revalidate it in CI.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MaxoPerf @maxoperf/maxoperfLoad & browser performance testing — drive MaxoPerf from your AI agent with your API key.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Stunt Double @stuntdouble/mcp-serverDeploy AI user personas to validate user journeys at scale. Find UX friction before real users do.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Playwright Network Chaos @vola-trebla/playwright-network-chaos-mcpMCP server that gives AI agents dynamic network chaos control over Playwright browser sessions10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Playwright Trace Decoder @vola-trebla/playwright-trace-decoder-mcpMCP server for unpacking and analyzing Playwright trace.zip archives4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Tactual @tactual-dev/tactualScreen-reader navigation cost analyzer. Scores AT user effort to find, reach, and operate content.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- ShotAPI MCP Server @smallhandsome/shotapi-mcp-serverScreenshot and HTML render MCP server for AI agents16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
