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 sirkirby/unifi-mcp --skill unifi-access-supportgit clone --depth 1 https://github.com/sirkirby/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/sirkirby/unifi-mcp/unifi-access-support)<a href="https://agentmods.dev/skills/sirkirby/unifi-mcp/unifi-access-support"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/unifi-access-support/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/sirkirby/unifi-mcp/unifi-access-support"><img src="https://agentmods.dev/badge/skills/sirkirby/unifi-mcp/unifi-access-support.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00031 | $0.00667 |
| Opus 5 | $0.00015 | $0.00333 |
| Sonnet 5 | $0.00006 | $0.00133 |
| Haiku 4.5 | $0.00003 | $0.00067 |
Grade A, and why
unifi-access-support 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 6d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- unifi-network-support — 88% identical, 14 lines differ
- unifi-protect-support — 88% identical, 16 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prepare a UniFi Access Support Bundle
Use access_get_support_bundle to collect the smallest useful, sanitized support bundle. The server
returns JSON only to the configured MCP client; this skill never posts, uploads, comments,
or opens an issue for the user.
Choose the Probe
- Start with
summary. It is local/cache-only and does not contact the controller. - Use
connectivityonly when connection or authentication behavior is relevant. Explain that it makes one bounded read-only request through the existing authenticated session, then ask for explicit confirmation before calling it.
If the user asks "show me what will be collected first," explain the selected probe and the included/excluded data classes before invoking the tool.
Generate
Call access_get_support_bundle(probe="summary") unless the user selected and confirmed another
supported probe. Never route this tool through *_execute, *_batch, a relay, or a
multi-location fan-out.
If the tool is missing, recommend updating the access plugin or package and
restarting the MCP client. If the server cannot start or register tools, use
$unifi-access-setup for setup help and fall back to the bug form's manual version,
controller, install, client, expected, actual, and reproduction fields. Do not ask for
credentials, raw configuration, controller payloads, or broad diagnostic logs.
Review Locally
Show the complete returned JSON to the user and pause before any external sharing. Tell them:
- The bundle is sanitized, not anonymous. Package/controller versions, runtime modes, capability flags, and coarse structural shapes can correlate or fingerprint an environment.
- It excludes credentials, controller addresses, identifiers, raw resource values, response bodies, raw exception text, logs, configuration files, and caller-supplied paths or endpoints.
UNIFI_MCP_DIAGNOSTICSlogs are a separate operator facility and are not automatically safe to post publicly.- They may remove optional sections or values they do not want to share, while keeping
schema_version,product,probe, and the relevant evidence when possible.
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.
- 6d ago First seen · 65 lines · 31 tokens per session scan A 87a8a9b5d182
unifi-access-support is a skill published in the GitHub repository sirkirby/unifi-mcp (809 stars, last pushed yesterday), licensed MIT. It adds 31 tokens to every session and 667 once invoked, about $0.0002 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 2026-09-06.
Other skills, from other repositories
streamdeck-designer
Design, theme, and author complete Stream Deck layouts for the user's hardware using the streamdeck-mcp tools. Use whenever the user wants a custom Stream Deck setup, asks for a themed deck (e.g. "hello-kitty Twitch deck", "retrowave music controls", "a dev deck for this repo"), wants buttons or dials configured for…
streamdeck-profile
Use this skill when you need to configure Elgato Stream Deck desktop profiles without taking USB control of the hardware.
kicad-review
Design review and validation workflow for KiCAD projects via MCP tools. Triggers on: "review my design", "check for errors", "audit", "DRC", "ERC", "find problems", "design review", "is this ready", "validate", "check my schematic", "check my PCB", "what's wrong", "run checks", "pre-fab review".
unifi-udm-pro-mcp
UniFi UDM Pro MCP Server for managing networks, connected clients, Wi-Fi settings, and device health via Model Context Protocol.
ips-cleanup
Audit and clean up an IP-Symcon system — recurring errors, red logs, instances in error state, dead objects. Triggers: "Fehler-Audit", "rote Logs", "tote Instanzen entfernen", "IPS-Health-Check".
pet-development
Use when developing, running, or debugging Commodore PET software (Commodore BASIC or 6502 assembly) on the VICE emulator with the pet CLI or the pet-tools MCP server. Covers the build/run/observe/debug loop, the stopped-state discipline, PET text encodings, and per-model differences.