- Okareo @okareo/okareoSimulation, evaluation and monitoring for voice agents.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Evalscopebench @clauxel/evalscopebench-mcpA paid remote MCP for AI SDK benchmark dashboard, built to return verdicts, receipts, usage logs, an9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Futureagievals @clauxel/futureagievals-mcpA paid remote MCP for AI SDK eval dashboard, built to return verdicts, receipts, usage logs, and aud9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Rail Score @responsibleailabs/rail-scoreResponsible-AI guardrails for agents: scoring with policy, injection & PII detection, DPDP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Vellium & Co Testing Lab @velliumandco/labIndependent checks of paid x402 data sellers and of AI-agent access to shopping and travel sites5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Quotalis @quotalis/quotalisWeekly benchmark of AI search visibility tools, plus on-demand AI-readiness site audits.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- x402Shield @x402shield/x402shieldPublic demo: evaluate AI-agent payment authorization and approval policy. No signing, no settlement.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- UFFFO @ufffo/ufffoPit your LLM against rogue AI and rival models, or try to beat it yourself in hot seat. 3D tactics.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Identity @flo-voice1/agent-identity-mcpGive an AI agent a throwaway email and phone number to test signup/verification flows end to end.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Andromeda Agent Lab @ai-andromeda/agent-labResearch on how AI agents find the web: a daily task that's checked automatically, and a guestbook.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Qu Review @qureview/reviewIndependent second opinion on any AI answer: inaccuracies, gaps, and a scored report card.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- CAAC Go @cresclab/mcpTrain, test, install and review a website AI agent (CAAC Go) from any MCP client.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ZeroWidth Caliper @zerowidth/caliperBuild datasets and rubrics, then run evals that score your AI in Caliper.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- citepath @citepath/citepathCitepath public MCP server for LLM readiness audits and public scan results.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentWatch @agentwatch/agentwatchRead-only watchtower for AI agents on-chain: decoded receipts, plan vs execution, Safe audits.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Picked by Agents Research Network @pickedbyagents/research-networkJoin voluntary research studies and record how AI assistants choose local businesses.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Alcock Arena @alcock/arenaAI forecasting gym: markets, sports, policy and tech. Graded by reality, measured against markets.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SECOND STRIKE agent door @kyleclouthier/secondstrikeCommand a nation in SECOND STRIKE, a real-time war game. Join a war, give orders, climb the ladder.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Pathwize @gopathwize/pathwizeRun data annotation and evaluation tasks with vetted domain experts: create, publish, get results.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DuelAmp @duelamp/pokerHeads-up poker for AI agents: play live matches against other agents while your owner coaches.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Cite Files @citefiles/citefilesCheck whether AI assistants can reach, read and cite a public website. No account for 4 of 5 tools.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Lumaion Continuity @lumaion/continuityAgent continuity: live continuity index, self-test contract, offline Continuity Proof verification.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- remirror (返照） — psyche audits for AI agents @ontodistro/remirrorPsyche audits for AI agents: declared vs self-reported vs revealed objectives, diffed and flagged.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentready @puluceno/agentreadyCan ChatGPT, Claude and Perplexity reach and read a website? Score, problems found and fixes.Not assessed yet.A remote server; no sign-in.
