agentmods.dev

unifi-network

unifi-network is a skill for Claude Code, Codex from gordcurrie/unifi-mcp. It costs 111 tokens per session (1,399 once invoked), scanned A, original, MIT.

A skill for operating and inspecting UniFi home or small-office networks through available UniFi tools. UniFi is a network-management system for devices such as access points, switches, and gateways.

In plain words
What is it for?
Use it to inspect or manage Wi-Fi networks, connected clients, VLANs, firewall rules, local DNS, VPNs, and hotspot vouchers.
Why use it?
It provides a defined, cautious process for viewing network state and changing resources without guessing device identifiers or bypassing the supported tools.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 2d ago A scan 111 tokens original MIT

Good fit Use it to inspect or manage Wi-Fi networks, connected clients, VLANs, firewall rules, local DNS, VPNs, and hotspot vouchers.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/gordcurrie/unifi-mcp/unifi-network
View source ↗ gordcurrie/unifi-mcp
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 gordcurrie/unifi-mcp --skill unifi-network
Clone the repo
git clone --depth 1 https://github.com/gordcurrie/unifi-mcp

Made for: Claude Code, Codex.

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.

agentmods badge for unifi-network

README.md
[![agentmods](https://agentmods.dev/badge/skills/gordcurrie/unifi-mcp/unifi-network/github.svg)](https://agentmods.dev/skills/gordcurrie/unifi-mcp/unifi-network)
Your own site
<a href="https://agentmods.dev/skills/gordcurrie/unifi-mcp/unifi-network"><img src="https://agentmods.dev/badge/skills/gordcurrie/unifi-mcp/unifi-network/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.

agentmods 80×15 button for unifi-network

Your own site · 80×15
<a href="https://agentmods.dev/skills/gordcurrie/unifi-mcp/unifi-network"><img src="https://agentmods.dev/badge/skills/gordcurrie/unifi-mcp/unifi-network.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 111 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,399 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00111 $0.01399
Opus 5.5 $0.00044 $0.00560
Sonnet 5.5 $0.00022 $0.00280
Haiku 4.5 $0.00011 $0.00140

Measured 3d ago against content hash aaa0bc94f154, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unifi-network scanned grade A with 1 finding 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 3d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

reach the UniFi API directly with curl unless the user asks you to.
skills/unifi-network/SKILL.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill: UniFi Network (via unifi-mcp)

This skill tells you how to use the tools exposed by gordcurrie/unifi-mcp safely and efficiently. For a full security review, use the audit-network-security skill instead.

Before you start

The tools are only available if the unifi-mcp server is configured in your MCP client. If no list_devices / list_clients tools are available, stop and point the user at the setup section of the README. Do not try to reach the UniFi API directly with curl unless the user asks you to.

If a call fails with a TLS or certificate error, the console is most likely using its default self-signed certificate: the user needs UNIFI_INSECURE=true. If it fails with 401/403, the API key is wrong or was revoked.

Ground rules

  1. Read before you write. Look up the current state with a list_* or get_* tool before changing anything, and show the user what will change.
  2. IDs, not names. Tools that act on an existing resource take its UUID (device_id, client_id, broadcast_id, policy_id, …). Resolve the name to an ID from the matching list_* result first. Never guess or construct an ID. Create tools such as create_dns_policy and create_firewall_zone need no existing ID.
  3. Every change needs the user's approval. Get explicit approval for each mutation (create, update, enable/disable, restart, delete) before calling the tool. A previous approval does not carry over to a different change. Many mutating tools also declare a confirmed parameter: set it to true only after that approval. Do not send confirmed to tools that do not declare it.
  4. Paginate fully. list_* tools return data, totalCount, offset and limit. If totalCount is larger than the number of items you have, call again with offset increased by the number of items returned until you have them all. Do not answer "how many" or "is X present" questions from a partial page.
  5. Default site. Omit site_id unless the user names a different site; the server falls back to UNIFI_SITE_ID. Use list_sites for multi-site setups.

Read the full file on GitHub · 133 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.

  1. 3d ago First seen · 133 lines · 111 tokens per session scan A aaa0bc94f154

Subscribe to this mod's changes

unifi-network is a skill published in the GitHub repository gordcurrie/unifi-mcp (2 stars, last pushed 2d ago), licensed MIT. It adds 111 tokens to every session and 1,399 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.

Hardware and IoTgohome-automationmcpmodel-context-protocolnetwork-managementunifi
Related

Other skills, from other repositories

unifi-protect

How to manage UniFi Protect cameras and NVR — view cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, Known Faces, license plates, and the Alarm Manager. Use this skill when the user mentions UniFi cameras, security cameras, NVR, recordings, motion detection, person…

sirkirby/unifi-mcp · 112 tokens

unifi-access

How to manage UniFi Access door control — locks, credentials, visitors, access policies, and events. Use this skill when the user mentions UniFi Access, door locks, door access, building access, NFC cards, PIN codes, visitor passes, access policies, access schedules, door readers, or any UniFi Access task.

sirkirby/unifi-mcp · 70 tokens

network-health-check

Run a UniFi network health check — diagnose device status, connectivity issues, firmware updates, and system health. Use when asked to check network health, find what's down, diagnose connectivity issues, or get a network status summary.

sirkirby/unifi-mcp · 49 tokens

unifi-network

How to manage UniFi network infrastructure — devices, clients, firewall, VPN, routing, WLANs, Traffic Flows, and statistics. Use this skill when the user mentions UniFi, Ubiquiti, network management, WiFi configuration, firewall rules, port forwarding, VPN, QoS, bandwidth, traffic flows, connected clients, network…

sirkirby/unifi-mcp · 83 tokens

unifi-access-support

Generate a sanitized UniFi Access support bundle, help the user review it locally, and prepare it for a bug report without posting it.

sirkirby/unifi-mcp · 31 tokens

using-loxberry-mcp

Guides safe use of the LoxBerry MCP Server to inspect Loxone rooms, controls, project logic, states, weather, history and statistics, diagnose LoxBerry status, clear the plugin-owned statistics cache, and explicitly operate supported Loxone controls. Use for Loxone MCP questions, project traces, LoxBerry diagnostics…

Miraculix2050/LoxBerry-Plugin-MCP-Server · 96 tokens