AI agents call list_pending_devices 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 performs a read-only operation—it lists/queries pending devices without side effects, no code execution, no data modification, and no destructive actions. The word 'List' combined with passive voice ('discovered...not yet adopted') confirms it retrieves status information only.
From the tool's definition Tool name 'list_pending_devices' and description 'List devices discovered on the network but not yet adopted' indicate a query operation that retrieves data without modifying or executing actions.
Attacks that exploit this kind of access
List devices discovered on the network but not yet adopted. 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_pending_devices: 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_pending_devices 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_pending_devices 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_pending_devices. 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_pending_devices 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 →