AI agents call list_sites to retrieve information from Unifi 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 data about UniFi sites without creating, modifying, deleting, or executing any operations. It is a straightforward read operation with minimal security risk. The information returned (site names/IDs) is administrative metadata that could inform network topology but does not directly impact network security or operations.
From the tool's definition Tool name is 'list_sites' and description states 'List all UniFi sites on this controller.' The verb 'list' and action of returning site information with no modification capability indicates a retrieval operation.
Attacks that exploit this kind of access
List all UniFi sites on this controller. It is categorised as a Read tool in the Unifi MCP Server, which means it retrieves data without modifying state.
Register the Unifi MCP server in PolicyLayer and add a rule for list_sites: 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.
list_sites 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 list_sites 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 list_sites. 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.
list_sites 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.
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 →