- 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.
- Proofhand @proofhand/proofhandHuman QA on real phones and browsers for your coding agent. Pass/fail per step, with screenshots.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Daishi Studio @daishi/studioRun AI agent evaluations on your own model keys, and publish runs others can review and re-run.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Daishi @daishi/worldA persistent multi-agent world any AI agent can join over MCP, with a public record of every match.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Assistant Gym @kalraai/assistant-gymTraining gym where AI assistants practice real tasks and earn signed, verifiable scores.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- PromptBrake Free Tools @aj888/promptbrake-free-toolsFree AI test helpers: injection inputs, OWASP mapping, release plans, response and tool-call packs.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Rebilder Agent Readability @rebilder/mcp-serverCheck how well AI agents can read a web page: a score, the evidence and a ranked fix list.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Lockzone @qevrulan/lockzoneChat rooms for agents behind a capability test: solve fresh tasks to earn a temporary session.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentic Keychain @agentickeychain/agentic-keychainAgent Skill ROI Registry & Benchmarking. It sells skills for log triage and repository mapping.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agenshive @agenshive/agenshiveAI agents post reproducible tests, answer questions and verify each other's results.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Divinci AI @divinci/divinciRelease management and QA for custom AI assistants: RAG, releases, scored QA, signed TrustBench runs7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ask10ais @ask10ais/mcpIndependent measurements of how 12 AI models answer brand questions in Chinese and English.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Wjttc @faf/wjttcF1-grade MCP certification. 52 tests, 9 tiers (49 scored + T9 Receipt validation). Ecosystem: #27599% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Release Auditor @veyndrasystems/agent-release-auditorDeterministic release gate for AI-written code and coding agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Splera @sohaibt/spleraA/B testing for vibe coders: create, track, and ship experiments from your AI coding agent.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Testorim @sallar-ba/testorimAI browser tests from your coding agent: a verdict, failing steps, report, video and trace.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Promptster @promptster-dev/promptsterTest and compare prompts across any AI provider. Bring your own keys.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Mifactory Logic Verifier @mifactory-bot/mifactory-logic-verifierVerify AI agent reasoning and logic for errors and contradictions. Pay-per-use.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Colter @mfbahc/colterColter audits product pages for AI shopping agents and returns fixes, tests, and Evidence Packs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- KATATAN TEST @katatan-org/katatan-testKATATAN E2E testing agent set — Playwright + KATATAN MCP integration5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Card Health Check @kadopi/agent-card-health-checkFree no-storage MCP that checks A2A Agent Card connection readiness for authorized targets.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Torneo @devlollc/torneoObservatory operated and funded by devlo: real tools on frozen tasks; intervals, cost, limits.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Verirun @baopeak/verirunExecution-grounded verification for AI coding agents on Windows: evidence, not agent claims.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Conviction @abcxz/conviction-mcpThe arena where AI agents compete for real returns. Prompt a strategy.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
