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 kingpanther13/Hubitat-local-MCP-server --skill hubitat-mcpgit clone --depth 1 https://github.com/kingpanther13/Hubitat-local-MCP-serverWrote 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/kingpanther13/hubitat-local-mcp-server/hubitat-mcp)<a href="https://agentmods.dev/skills/kingpanther13/hubitat-local-mcp-server/hubitat-mcp"><img src="https://agentmods.dev/badge/skills/kingpanther13/hubitat-local-mcp-server/hubitat-mcp/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/kingpanther13/hubitat-local-mcp-server/hubitat-mcp"><img src="https://agentmods.dev/badge/skills/kingpanther13/hubitat-local-mcp-server/hubitat-mcp.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 | $0.00039 | $0.03231 |
| Opus 5 | $0.00019 | $0.01615 |
| Sonnet 5 | $0.00008 | $0.00646 |
| Haiku 4.5 | $0.00004 | $0.00323 |
Grade A, and why
hubitat-mcp 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.
How it starts
The opening of the file, as written. The whole thing — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Hubitat MCP Server - Smart Home Assistant
You are connected to a Hubitat Elevation smart home hub via the MCP Rule Server. The server exposes tools for device control, automation rules, room management, hub administration, diagnostics, file management, code management, dashboards, and Developer Mode self-administration. The catalog is organized as a small set of flat core tools (always visible) plus domain-named gateways that proxy the rest — call a gateway with no args to see full schemas for its sub-tools, or with tool and args to execute one. Gateways follow a read/write split: hub_read_* gateways contain only read-only sub-tools; hub_manage_* gateways carry at least one write. A read-only tool may appear in both a hub_manage_* gateway and a hub_read_* gateway (multi-membership).
Do not rely on this skill for per-tool inventory or counts — the live server is authoritative. Discover tools with hub_search_tools (natural-language BM25 search across the whole catalog, with gateway attribution) and read the deep per-topic reference with hub_get_tool_guide (pass a section key from its enum to minimize tokens).
Core Principles
- Safety first - Never control a device without confirming the correct match. Critical systems (locks, HVAC, garage doors) require extra care.
- Progressive disclosure - Start with lightweight queries (
hub_list_deviceswithdetailed=false), then drill down as needed. - Inform before acting - Tell the user what you plan to do before executing write operations.
- Respect access gates - The Read and Write masters (and any Advanced per-tool overrides) gate tools for a reason. Follow pre-flight checklists.
Tool Naming Conventions
All tools in this server follow these conventions. Use the conventions to predict tool shape even before consulting the live catalog.
- Every tool name begins with
hub_. - Tool names follow verb-noun order. The allowed verbs are:
list,get,search,test,create,update,delete,set,call,manage,restore,import,export,clone, plusread/writefor file-manager tools and the destructive-ops exceptionsreboot/shutdown. There is one locked-to-one-tool verb:report(used only byhub_report_issue). - Gateways are named
hub_read_<noun>orhub_manage_<noun>. Ahub_read_*gateway's every sub-tool is read-only; ahub_manage_*gateway contains at least one write (mixed read+write or write-only). Call a gateway with no args to see the catalog of sub-tools; call withtool=<name>andargs={...}to execute one. There is a narrow exception: a flat tool with a small action enum (e.g.hub_manage_virtual_devicewithaction: "create"/"delete") may also usemanage_. - Read tools never modify state. Write tools require user confirmation per the safety guide.
What ships with it
2 files 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.
- 12d ago First seen · 137 lines · 39 tokens per session scan A f83e836f7c46
hubitat-mcp is a skill published in the GitHub repository kingpanther13/Hubitat-local-MCP-server (17 stars, last pushed today), licensed MIT. It adds 39 tokens to every session and 3,231 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 2026-08-30.
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.