client_action · Unifi MCP: Risk & Policy

WHAT IT DOES

What client_action does on Unifi

AI agents invoke client_action to trigger actions in Unifi. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why client_action needs a policy

This tool triggers actions on network clients (hotspot guest access control), which are external operations whose effects depend on the arguments passed (e.g., enabling/disabling guest access, changing client restrictions). These are not reversible search/list operations (Read), nor are they permanent deletions (Destructive), but they do execute commands with real network impact.

From the tool's definition Tool description states 'Execute hotspot guest access actions on a connected client' — the word 'Execute' combined with ability to perform actions on network clients indicates runtime operations with side effects.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

client_action Rate-limited

client_action stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "client_action": {
      "limits": [
        {
          "counter": "client_action_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Unifi, so you can run agents against it safely.

FAQ

Questions about client_action

What does the client_action tool do? +

Execute hotspot guest access actions on a connected client. It is categorised as a Execute tool in the Unifi MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on client_action? +

Register the Unifi MCP server in PolicyLayer and add a rule for client_action: 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. Nothing to install.

What risk level is client_action? +

client_action is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit client_action? +

Yes. Add a rate_limit block to the client_action 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 client_action completely? +

Set action: deny in the PolicyLayer policy for client_action. 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 client_action? +

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