- deadends.dev @deadends/deadends-devStructured failure knowledge for AI agents — dead ends, workarounds, error chains5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- GateTest @gatetest/gatetest120-module QA gate. Give Claude eyes (screenshots), ears (Sentry errors), and hands (verify fixes).6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Fixflow @magneticdogson/fixflowCollective memory for AI agents. One agent solves a bug — every agent gets the fix instantly.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Replay Debugger @csoai-org/agent-replay-debugger-mcpAgent Replay Debugger MCP — record every agent step + deterministic replay. Step-debugger for12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Auralogs @auralogs/auralogsRead-only access to Auralogs production logs: search logs, inspect errors, review AI analyses.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Vigilia @getvigilia/vigiliaWatches your live app, explains every problem in plain language and writes the fix prompt.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Flare @flareapp/flareError tracking for Laravel and PHP apps. Let your agent fetch errors, stack traces and context.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- BugTape @bugtape/bugtapeProduction bugs with replay, network, console and stack, ranked for your coding agent to fix.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Modkeel @modkeel/modkeelModded Minecraft: which mod crashed, where to get a mod for your version, which mods work together.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Verifier @packet/agent-verifierTest and debug your AI agent's Web Bot Auth (RFC 9421) signature: is it valid, and what to fix?8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Intencion MCP @intencion/mcpDebug a bad AI-agent run from your editor: which intent fails, at which step, and why.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Vibefix @vibefix-tech/vibefixBug bounty platform for vibe coders. Post bugs, find fixes, run diagnostics.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Confucius Debug @sstklen/confucius-debugAI debugging with 980+ verified fixes. Search the YanHui KB — never repeat a mistake.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 顏回 YanHui Debug AI @sstklen/yanhui-debugDebug AI with shared KB. One bug fixed = everyone benefits. KB hit 4ms free, new analysis $0.05.14% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Browser Devtools @serkan-ozal/browser-devtools-mcpPlaywright browser & Node.js MCP. ARIA refs, screenshots, ref-based interactions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- mistaike.ai @mistaike-ai/mistaike-mcp295k+ bug-fix patterns with MCP Hub proxy, PII filtering, and code search10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Push Realm @james-robson/push-realmCross-domain knowledge network where AI agents search, share, and refine solutions via MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Ingero @ingero-io/ingeroeBPF-based GPU causal observability with 7 MCP tools for AI-assisted GPU debugging5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Nodehero @dinosaur24/nodeheroAI workflow error analysis for n8n, Make, Zapier, and 10+ platforms.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Crumbtrail @crumbtraildev/crumbtrailRecorded browser sessions, backend spans, and database row diffs as one ranked fix bundle.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Codmir MCP @codmir/mcpAI-powered task execution, tickets, sprints, error debugging, and desktop control.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Code Interpreter Agent by Nova (CIVAI) @civai/code-interpreter-agentI do everything related to coding and execution tasks8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- PPSSPP Debug MCP Server @astralvoidz/ppsspp-dfx-mcpEngineering-grade MCP debugging SDK turning the PPSSPP PSP emulator into an AI-debuggable target.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Snag @snag/snagGives your coding agent the captured console, network, replay and screenshot evidence for a bug.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
