AI agents use set_client_name to create or update resources in UniFi MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your UniFi MCP environment.
The tool modifies client configuration (name/metadata) reversibly within the UniFi controller, which is a write operation. Not destructive because renaming is reversible. Not execute because it doesn't run arbitrary code. Severity is medium because misuse could cause network confusion or aid in reconnaissance, but impacts are contained to client metadata rather than network-wide disruption.
From the tool's definition Tool name 'set_client_name' indicates modification of client metadata. No description provided, but sibling tools like 'block_client', 'forget_client', and 'authorize_guest' suggest this server performs network administration actions including client…
Documented attack patterns abuse exactly the kind of access set_client_name gives an agent:
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 set_client_name:
{
"version": "1",
"default": "deny",
"tools": {
"set_client_name": {
"limits": [
{
"counter": "set_client_name_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
} set_client_name 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.
Free to start. No card required.
set_client_name. It is categorised as a Write tool in the UniFi MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the UniFi MCP server in PolicyLayer and add a rule for set_client_name: 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.
set_client_name is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the set_client_name 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.
Set action: deny in the PolicyLayer policy for set_client_name. 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.
set_client_name 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.
Start from UniFi MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
29 UniFi MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.