- Owl24 @madnands5/owl24-mcpHand a production error to the coding agent you already use — it claims it and writes the fix.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Dev error explainers @mahdibrr/dev-error-explainersOffline, deterministic cause and fix for Node, npm, Next.js, CORS and Postgres URL errors.Not assessed yet.Runs on your machine, installed from npm.
- deadends.dev @dbwls99706/deadends-devStructured failure knowledge for AI agents — dead ends, workarounds, error chains4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Trigger.dev MCP by usefulapi @usefulapi/trigger-devDebug background jobs — runs, traces, spans, schedules, queues and deployments.Not assessed yet.A remote server; no sign-in.
- Flutter Lamp @itsonu/flutter-lampLive runtime data from a running Flutter app: exceptions, logs, network, frames, diagnosis.Not assessed yet.Runs on your machine, installed from npm.
- Narshamcp @next-stage-inc/narshamcpUnreal Engine MCP server: C++ PDB symbols, Blueprint and .uasset analysis, build-error fixes4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- NAIF Gravity @naief9961-tech/naif-fixgraphAI agent and MCP diagnostics, API/auth/webhook repair, JSON validation and bounded recovery.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Codna — repository intelligence @thyn-ai/codnaRepo intelligence: triage, fix PRs, SARIF reachability, recall. Free codna login to execute.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Exnos @golproductions/exnosRead-only live state of your Chrome tabs for AI agents: fields, console errors, network, storage.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Snapback @ra1labsworkx-wq/snapbackDiagnose why an AI agent failed and get the verified fix instantly. Free, no token.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Heystack @heystack/heystackObservability for AI apps: investigate traces, logs, LLM usage, replays and crashes; manage alerts.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Titan Frameworks (LangChain, LlamaIndex, Ollama, XRPL) @bebopp187-stack/titan-frameworksReview and rewrite LangChain, LlamaIndex, Ollama, and XRPL code against current APIs.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Tracehub @mcpsmiths/tracehub-mcpQuery OTel traces across Jaeger, Tempo, Traceloop, Datadog, Sentry, X-Ray, New Relic, Honeycomb.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Billing Doctor @lazytitan30/billing-doctorDiagnose Google Play Billing incidents locally, with evidence. Not affiliated with Google.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- OmniDebugLink @omnidebuglink/omnidebuglinkremote debug iOS/Android/Unity/Godot/Flutter/RN/Web on real-device.ui-tree/screenshots/taps,tests.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- FailTrace @lbarimi/failtraceDebugging experiments for coding agents: reproduce failures and verify fixes with test evidence.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- VibeFix @vibe-fixer/vibefixTests your live app like a first customer, free. One exact fix to paste in your builder, re-tested.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Verdict @dgotlieb/verdict-mcpSandboxed test runs for coding agents: compact typed verdicts with failure fingerprints and history3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Qlane @qlane/qlaneAI QA that runs your app in a browser on every pull request: projects, test targets, test cases.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Chrome DevTools MCP @async23/chrome-devtools-mcpMCP server for Chrome DevTools10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- NATS Trail @solsolettidev/nats-trailRead-only NATS and JetStream observability: trace a request across streams, rank what is broken.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Cirdan @adanb13/cirdanAI infrastructure cartographer & MCP server: fingerprints, graphs & watches live infra for agents7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Observability @rudrendupaul/agent-observabilityAI agent observability with deterministic record/replay for debugging agent failures.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Python Code Validator @statemind/python-code-validatorProves AI-generated Python does what you asked: lint, types, security, sandbox run, exact fixes.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
