manage_client · Unifi MCP: Risk & Policy

WHAT IT DOES

What manage_client does on Unifi

AI agents use manage_client to create or update resources in Unifi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unifi environment.

WHY IT NEEDS A POLICY

Why manage_client needs a policy

This tool creates or modifies client metadata (friendly names/aliases) without deleting data, executing code, or causing financial impact. The change is reversible by updating the alias again. While it operates on network infrastructure, the blast radius is minimal since renaming a client has no impact on network connectivity, security posture, or data access.

From the tool's definition Tool description states 'Set or update the friendly name (alias) for a network client' — this performs a reversible modification operation (update).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

manage_client Rate-limited

manage_client stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "manage_client": {
      "limits": [
        {
          "counter": "manage_client_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

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 manage_client

What does the manage_client tool do? +

Set or update the friendly name (alias) for a network client. It is categorised as a Write tool in the Unifi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on manage_client? +

Register the Unifi MCP server in PolicyLayer and add a rule for manage_client: 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 manage_client? +

manage_client is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit manage_client? +

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

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

manage_client 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.