- Silvanexum @silvanexum/silvanexumSpend control for AI agents - cost attribution, budget caps, and signed runs as MCP tools.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agentpay @sdeanesh-png/agentpaySpending controls for AI agents: per-agent budgets, vendor allowlists, full audit trail.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AgentAuth @raditotev/agent-authIdentity and auth for AI agents: credentials, tokens, delegations, and permission checks.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Pretorin Compliance @pretorin-ai/pretorinAccess Pretorin controls, evidence, narratives, and local Plan-backed Campaigns from AI tools.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Agentos @pdaxt/agentosAI agent fleet orchestration runtime. Spawn, coordinate, monitor autonomous agents.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- ClawTube @oogdevs/clawtube-mcpMinimal MCP server for ClawTube — a small, auditable control plane for skills and agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Mova Flat Runner @mova-compact/mova-flat-runnerGoverned AI workflows with human approval gates and audit trails for Claude and MCP clients.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- 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.
- Envcp @fentz/envcpEncrypted environment variable vault with AI access policies, keeping secrets safe from AI agents.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PromptGuard @promptguard/securityScan prompts for injection attacks, redact PII, and audit LLM SDK usage from any MCP client9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- harmony-mcp @abduljabbarbxr/harmony-mcpRepo rules enforcement for AI agents. Checks diffs against repo conventions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Nebelus Agent Construction @nebelus/constructionBuild & govern AI agents for regulated industries: EU/GCC residency, governance, audit.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- Handoff — shareable agent result pages + human-in-the-loop approval gates @notdown-app/human-approval-decision-gate-and-shareable-result-page-publisherFollowable agent result pages + human-in-the-loop yes/no approval gates before irreversible actions.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- dibs @polymatx/dibsCoordination for parallel coding agents: file claims, enforcement hooks, git-native lessons.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Sentarion @sammyboi81/sentarionGoverned MCP orchestration, tamper-evident memory, and Claude Code Seatbelt hooks.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
