get_alarms

THE RISK

Low Risk

Why get_alarms needs a policy

This tool retrieves alarm information from the UniFi controller for monitoring and visibility purposes. It queries existing data without modifying, deleting, or executing any operations. The action is read-only and poses minimal risk if misused by an AI agent.

From the tool's definition Tool name is 'get_alarms' and description states 'Get controller alarms' — a retrieval operation with no side effects.

Documented attack patterns abuse exactly the kind of access get_alarms gives an agent:

POLICY

How to control get_alarms

PolicyLayer is an MCP gateway — it sits between your AI agents and UniFi MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for get_alarms:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "get_alarms": {}
  }
}

get_alarms is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

Create a free account and register UniFi MCP — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

CAP THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More UniFi MCP tools

Destructive forget_client Remove historical data for a client (GDPR compliance). Execute restart_device Restart a UniFi device. Execute start_spectrum_scan Start RF spectrum scan on access point. Execute authorize_guest authorize_guest Execute block_client Block a client from accessing the network. Execute locate_device Trigger locate LED on a UniFi device. Execute reconnect_client Force reconnection of a client device. Write unblock_client Unblock a previously blocked client.

All 29 UniFi MCP tools →

Read tools on other servers

M-Team MCP Server get_torrent_detail YouTube MCP Server search_channel Android Forensics ADB MCP Server parse_browser_history 0xarchive web3_challenge

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Data exfiltration → How read access becomes an exfiltration channel when chained with untrusted content.
MCP token cost → What connecting this server costs in context-window tokens on every request.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about get_alarms

What does the get_alarms tool do? +

Get controller alarms. It is categorised as a Read tool in the UniFi MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on get_alarms? +

Register the UniFi MCP server in PolicyLayer and add a rule for get_alarms: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches UniFi MCP. Nothing to install.

What risk level is get_alarms? +

get_alarms is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit get_alarms? +

Yes. Add a rate_limit block to the get_alarms rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block get_alarms completely? +

Set action: deny in the PolicyLayer policy for get_alarms. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides get_alarms? +

get_alarms is provided by the UniFi MCP server (jmagar/unifi-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every UniFi MCP tool call.

Start from UniFi MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →