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.
npx skills add devjourney/unifi-mcp --skill unifi-protectgit clone --depth 1 https://github.com/devjourney/unifi-mcpWrote 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.
[](https://agentmods.dev/skills/devjourney/unifi-mcp/unifi-protect)<a href="https://agentmods.dev/skills/devjourney/unifi-mcp/unifi-protect"><img src="https://agentmods.dev/badge/skills/devjourney/unifi-mcp/unifi-protect/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.
<a href="https://agentmods.dev/skills/devjourney/unifi-mcp/unifi-protect"><img src="https://agentmods.dev/badge/skills/devjourney/unifi-mcp/unifi-protect.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00112 | $0.01494 |
| Opus 5 | $0.00056 | $0.00747 |
| Sonnet 5 | $0.00022 | $0.00299 |
| Haiku 4.5 | $0.00011 | $0.00149 |
Grade A, and why
unifi-protect 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 10d 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.
This is a copy
100% identical to unifi-protect — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
UniFi Protect MCP Server
You have access to a UniFi Protect MCP server that lets you query and manage a UniFi Protect NVR. It provides 61 tools covering cameras, smart detections, Find Anything detection search, recordings, snapshots, lights, sensors, chimes, Known Faces, license plates, and the Alarm Manager (arm/disarm).
Tool Discovery
The server uses lazy loading by default — only meta-tools are registered initially:
| Meta-Tool | Purpose |
|---|---|
protect_tool_index |
Discover tools by name/description; use category, search, or include_schemas to filter |
protect_execute |
Call any tool by name (essential in lazy mode) |
protect_batch |
Run multiple tools in parallel |
protect_batch_status |
Check async batch job status |
Workflow: Call protect_tool_index to find the right tool, then protect_execute to call it. Use protect_batch for multiple independent queries.
Safety Model
All mutations are disabled by default because Protect controls physical security hardware.
Read operations — always available. Listing cameras, events, snapshots, sensor readings — all work without permissions.
Mutations require explicit opt-in via env vars:
UNIFI_POLICY_PROTECT_CAMERAS_UPDATE=true— camera settings, recording toggle, PTZ, rebootUNIFI_POLICY_PROTECT_LIGHTS_UPDATE=true— light brightness, PIR sensitivityUNIFI_POLICY_PROTECT_CHIMES_UPDATE=true— chime volume, triggerUNIFI_POLICY_PROTECT_ALARM_UPDATE=true— arm/disarm the Alarm Manager (Protect 6.1+)UNIFI_POLICY_PROTECT_RECOGNITION_UPDATE=true— Known Face rename/mergeUNIFI_POLICY_PROTECT_RECOGNITION_DELETE=true— Known Face deletion
Confirmation flow — every mutation uses preview-then-confirm:
- Default call → returns preview of what would change
- Call with
confirm=true→ executes the mutation
Always preview first and show the user before confirming.
Response Format
All tools return: {"success": true, "data": ...}, {"success": false, "error": "..."}, or {"success": true, "requires_confirmation": true, "preview": ...}. Always check success first.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 92 lines · 112 tokens per session scan A bf797a4fbca9
unifi-protect is a skill published in the GitHub repository devjourney/unifi-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 112 tokens to every session and 1,494 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to unifi-protect, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
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…
jetson-diagnostic
Read-only Jetson health snapshot for identity, memory, GPU, thermal, power, storage, services, and top processes.
doca-socket-relay
Use this skill when the operator is driving the DOCA Socket Relay to bridge a socket-oriented host application onto a BlueField DPU peer without rewriting it — picking the deployment shape (in-process, sidecar, or BlueField service container), configuring the host-side socket and the DPU-side forwarding endpoint…
offensive-z-wave
Z-Wave attack methodology — sniffing with Z-Force / EZ-Wave / RTL-SDR + ZniffMobile, S0 (legacy) network-key derivation flaw and key reuse, S2 (modern) ECDH commissioning analysis, replay/injection on unauthenticated nodes, default-key brute-force on test deployments, and home-automation hub pivots. Use when targeting…
hsb-flash
Flash the FPGA on an HSB board connected to an NVIDIA devkit. Supports HSB Lattice boards (FPGA versions 2407, 2412, 2507, 2510) and Leopard Imaging VB1940 "all-in-one" cameras (FPGA versions 2507, 2510). Uses release-specific YAML manifests and board-type-specific program commands. Lattice and VB1940 commands must…
jetson-validate-image
Use after jetson-flash-image to run static BSP checks, on-target smoke/regression tests on a flashed DUT, or both. Not for build or flash steps. Triggers: validate bsp, on-target validation.