AI agents call list_dpi_apps 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 retrieves metadata about DPI application classifications—a read-only information lookup operation. No data is created, modified, deleted, or any external operation is triggered. The blast radius of misuse is minimal; an AI agent cannot cause harm by listing DPI app categories.
From the tool's definition Tool name 'list_dpi_apps' and description 'List DPI...applications' indicate a retrieval operation that queries and returns data about DPI application categories without modifying system state.
Attacks that exploit this kind of access
List DPI (Deep Packet Inspection) application categories and applications. 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_dpi_apps: 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_dpi_apps 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_dpi_apps 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_dpi_apps. 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_dpi_apps 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 →