unifi-api · UniFi MCP Server MCP: Risk & Policy

WHAT IT DOES

What unifi-api does on UniFi MCP Server

AI agents invoke unifi-api to trigger actions in UniFi MCP Server. 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 unifi-api needs a policy

This tool allows execution of arbitrary UniFi API calls with no restriction on method or endpoint. An AI agent could use it to delete devices, modify firewall rules, reconfigure network infrastructure, or perform any other destructive or disruptive action. The 'escape hatch' framing explicitly acknowledges it bypasses the guardrails of other tools.

From the tool's definition "Generic UniFi API escape hatch. Make any API call not covered by other tools." — arbitrary API calls with configurable path and absolute path override

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

unifi-api Rate-limited

unifi-api 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": {
    "unifi-api": {
      "limits": [
        {
          "counter": "unifi-api_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 MCP Server, so you can run agents against it safely.

FAQ

Questions about unifi-api

What does the unifi-api tool do? +

Generic UniFi API escape hatch. Make any API call not covered by other tools. Path is relative to /proxy/network/api/s/{site}/ unless useAbsolutePath is true. It is categorised as a Execute tool in the UniFi MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on unifi-api? +

Register the UniFi MCP Server MCP server in PolicyLayer and add a rule for unifi-api: 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 Server. Nothing to install.

What risk level is unifi-api? +

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

Can I rate-limit unifi-api? +

Yes. Add a rate_limit block to the unifi-api 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 unifi-api completely? +

Set action: deny in the PolicyLayer policy for unifi-api. 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 unifi-api? +

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