Retrieve active or known clients for a UniFi site
AI agents call get_clients to retrieve information from Unifi Network without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns information about connected clients on a UniFi network without modifying any data or triggering side effects. It is a straightforward read operation with low risk—the worst outcome would be information disclosure about network clients, which is limited in impact compared to modification, deletion, or execution capabilities.
From the tool's definition Tool name 'get_clients' and description 'Retrieve active or known clients for a UniFi site' indicate a data retrieval operation. Server is explicitly described as 'Read-only MCP server'.
Attacks that exploit this kind of access
Retrieve active or known clients for a UniFi site. It is categorised as a Read tool in the Unifi Network MCP Server, which means it retrieves data without modifying state.
Register the Unifi Network MCP server in PolicyLayer and add a rule for get_clients: 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 Network. Nothing to install.
get_clients is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_clients 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 get_clients. 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.
get_clients is provided by the Unifi Network MCP server (unifi-network-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →