A guide for setting up and diagnosing UniFi remote access VPNs using WireGuard or Teleport. A VPN creates an encrypted connection from a phone or computer to a home or office network.

Use it to create VPN clients, configure connection details, check firewall and routing settings, and diagnose tunnel problems from outside the network.

It helps find why a VPN does not connect, connects without reaching devices, or runs slowly. It also helps avoid exposing network services directly to the internet with port forwarding.

unifi-vpn — Skill for Claude Code by mikeholownych

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add mikeholownych/unifi-mcp --skill unifi-vpn

Clone the repo

git clone --depth 1 https://github.com/mikeholownych/unifi-mcp

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-vpn/github.svg)](https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-vpn)

Your own site

<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-vpn"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-vpn/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mikeholownych/unifi-mcp/unifi-vpn"><img src="https://agentmods.dev/badge/skills/mikeholownych/unifi-mcp/unifi-vpn.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 69 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 731 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00069	$0.00731
Opus 5	$0.00034	$0.00365
Sonnet 5	$0.00014	$0.00146
Haiku 4.5	$0.00007	$0.00073

Measured 12d ago against content hash 02dd8ddca4f3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

unifi-vpn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/unifi-vpn/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UniFi VPN (WireGuard / Teleport)

Remote access done right: prefer inbound VPN over any port-forward exposure. Covers setup, and the three classic failure modes.

Step 0

get_sysinfo (version facts 10.x). get_firewall_policies: note the EXTERNAL zone id and whether a VPN zone exists; get_site_health wan subsystem.

Setup checklist (WireGuard user on UDM/UCG — UI-driven; no MCP CRUD tool)

Controller: Settings → VPN → WireGuard (or Teleport for quick links) → create server, add client profile, export config/QR to the phone.
Note the listen port (default 51820/udp). If the controller does not open it externally, add forward + zone policy exactly per unifi-port-forwarding (udp only).
Client side: endpoint = public IP/DDNS hostname; keep default AllowedIPs (0.0.0.0/0) for full-tunnel, or split-tunnel subnets only.
Verify from cellular (not the same LAN).

Failure-mode ladder (diagnose in this order)

Symptom	Meaning	Fix direction
No handshake at all	packets not arriving	wrong endpoint/port, UDP blocked by ISP/carrier, key mismatch
Handshake OK, zero data	routing/firewall	AllowedIPs on client missing target subnets; VPN→LAN zone policies absent
Reach some zones, not others	zone-firewall scoping	create ALLOW policies VPN-zone→each needed zone (per-pair rules!)
Connects, websites hang, small pings fine	MTU	lower client MTU to ~1380–1420 (double-NAT/PPPoE overhead)
Works then dies after N min	NAT/idle timeout	persistent keepalive 25s on client

Zone firewall specifics (Network 9+/10)

VPN clients typically land in a dedicated VPN/Guest zone that is BLOCKED from internal zones by predefined catch-alls. "Connected but can't reach LAN" is almost always missing ALLOW policies from the VPN zone to HOME/Servers/etc. Create them scoped (not ANY) with create_firewall_policy, mirroring how per-device grants work — plus the auto-generated Return companions.
Check hit counters on those rules while the client attempts traffic: hits=0 ⇒ problem is client-side (AllowedIPs), hits rising but failing ⇒ service/port issue.

Read the full file on GitHub · 61 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 61 lines · 0 tokens per session scan A 02dd8ddca4f3

Subscribe to this mod's changes

unifi-vpn is a skill published in the GitHub repository mikeholownych/unifi-mcp (0 stars, last pushed 12d ago), licensed MIT. It adds 69 tokens to every session and 731 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Cloud DevOps and cloud

gke-compute-classes

Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto…

google/skills · 83 tokens

gke-reliability

Improves GKE workload reliability, using PDBs, health probes, and topology spread constraints. Use when configuring GKE workload reliability, setting up PDBs, or configuring GKE health probes (liveness, readiness, startup). Don't use for disaster recovery setup or full cluster backups (use gke-backup-dr instead).

google/skills · 73 tokens

gke-workload-security

Audits, configures, and hardens workload-level security controls for Google Kubernetes Engine (GKE) applications and namespaces. Covers running cluster security audits (auditcluster.sh), configuring Workload Identity Federation (impersonation, KSA/GSA binding, and pod setup), enforcing Network Policies (default-deny…

google/skills · 181 tokens

nemo-automodel-launcher-config

Configure NeMo AutoModel job launches for interactive runs, Slurm clusters, and SkyPilot cloud execution.

NVIDIA/skills · 30 tokens

azure-mgmt-botservice-dotnet

Azure Resource Manager SDK for Bot Service in .NET. Management plane operations for creating and managing Azure Bot resources, channels (Teams, DirectLine, Slack), and connection settings. Triggers: "Bot Service", "BotResource", "Azure Bot", "DirectLine channel", "Teams channel", "bot management .NET", "create bot".

microsoft/skills · 78 tokens

cloud-architect

Designs cloud architectures, creates migration plans, generates cost optimization recommendations, and produces disaster recovery strategies across AWS, Azure, and GCP. Use when designing cloud architectures, planning migrations, or optimizing multi-cloud deployments. Invoke for Well-Architected Framework, cost…

Jeffallan/claude-skills · 71 tokens