- STACK @getstack-run/stackCommand your AI agents: verifiable passports, credential injection, full audit, revoke in 60s.37% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Dobby @gil-dobby/dobbyConnect, monitor, and control AI agents — tasks, approvals, schedules, and governance.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- GeraWitness @geraservicesuk/mcp-gera-witnessGeraWitness MCP (placeholder) — human-in-the-loop safety layer for AI agents. Launching 2026.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Creator Desk Agent Supervisor @creatordeskai-prog/creator-desk-agent-supervisorAgent completion verification with defects, corrections, and evidence receipts.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- aaaa-nexus — Formally Verified AI Safety APIs @atomadictech/aaaa-nexusFormally verified AI safety APIs. Pay-per-call via USDC (x402). 75+ endpoints, no signup.20% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- ACF @aiconsulting06000-tech/acf-mcpOfficial ACF® MCP server — Agentic Commerce Framework® governance copilot for AI assistants.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- EP AgentIAM @achilliesbot/ep-agentiamAI agent execution safety via x402 micropayments: risk scoring, integrity, memory checks10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Ac Jobs @wchampe/ac-jobsAdmission gate for AI agents: submit a step, get admit/hold/reject vs your constitution.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- AiEGIS @velogerber/aiegisAI agent security and governance. Register, verify, scan, and monitor agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TrigGuard @trigguard-ai/trigguardDeterministic execution authorization for AI agents and automated systems.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- StackFast FractWin Expert Brain @trupe-rs/expert-brainExpert knowledge base for sales, negotiation, strategy, operations, and risk.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2A Trust Plane @the-825/a2a-trust-planeTenant-scoped control layer for agent-to-agent systems: governed routing, approvals, evidence.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Elite Reasoning @snehgabani/elite-reasoning-mcpEvidence-gated verification, selection, and measurement MCP for coding agents.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- SentinelGate @sentinel-gate/sentinelgateOpen-source MCP proxy for AI agent access control with CEL policies, RBAC, and audit.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
- SpineFrame @ratnaditya-j/spineframeGovernance runtime for AI agents with signed provenance, compliance audits, and OSINT.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agentlock @olum289/agentlockSecurity gateway for AI agents: policy, approval, and audited execution, no secrets shared.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Warden @larshiensch99/wardenRegister every AI agent, log every action, prove it. EU AI Act compliance built in.15% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Fulcrum @dewars30/fulcrumAI governance MCP server for policy enforcement, cost control, and observability.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Autonomy Foundry Governance @diegomul/autonomy-foundry-governanceGovernance and agentic-commerce policy tools for AI agents: spend, purchase and charter controls.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- VaultCrux Memory Core @cuecrux/vaultcrux-memory-coreVaultCrux Memory Core — 32 tools: knowledge, decisions, constraints, signals, coverage11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Neon Zero-Trust MCP Gateway @ansarii/zero-trust-mcp-gatewayAI security firewall & DLP proxy protecting API keys and blocking destructive commands.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AgentKYB @andy229651/agentkybFree local payment guard for AI agents plus paid deep vendor KYB via x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Clevername @alexfloyd13/clevername-mcpAI agent governance — security scanning, BYOK routing, audit logging, and Council approvals.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Rules MCP @akr1166/rules-mcpMCP for rules/skills/knowledge evaluation for Cursor, Claude, VS Code, and Antigravity.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
