UniFi Gateway runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 17 Sep 2026.
Safe-by-default UniFi MCP: Network + Protect + Access, multi-site, dry-run, audit log.
Today is the operative word: we check UniFi Gateway every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Safe Google Workspace admin for AI agents: read-only by default, confirm-gated deletes, audit log.
Security-first SendGrid MCP server: dry-run default, recipient allowlists, rate caps, audit log.
MCP gateway for controlled SSH access with per-client auth, command policies, and audit logging.
Kubernetes monitoring & ops for AI agents — safe-by-default access modes and guards.
Policy-gated, audited SSH for Linux and Windows hosts: roles, approvals, and an audit log.
Safe-by-default SQL guardrails for AI agents: AST-checked queries, per-table policy, audit log.
Production-grade MCP Gateway in Go with RBAC, in-flight PII redaction, and audit logging.
MCP policy proxy: spend caps, approvals for destructive tools, kill switch, dry-run, audit log.
Answers built from our own checks of this server.