AI agents use manage_traffic_rule to create or update resources in Unifi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Unifi environment.
While the tool includes 'delete' operations, the primary context is managing traffic matching lists—configuration rules rather than irreversible system data. The tool is primarily a Write operation (create/update) with some Destructive potential (delete rules). However, deleting traffic rules is generally reversible through recreation and lacks the finality of destroying critical data or user content.
From the tool's definition Tool description states 'create, update, or delete traffic matching lists' indicating reversible modification and deletion capabilities on network traffic rules.
Attacks that exploit this kind of access
List, create, update, or delete traffic matching lists. It is categorised as a Write tool in the Unifi 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 manage_traffic_rule: 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.
manage_traffic_rule 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 manage_traffic_rule 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 manage_traffic_rule. 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.
manage_traffic_rule 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 →