AI agents use manage_vouchers 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.
The tool's primary capability is creating vouchers (Write operation). While it includes deletion, vouchers are access tokens rather than critical irreversible data—deletion is reversible by simply creating new ones. The 'list' operation is Read-only. The most severe applicable category is Write.
From the tool's definition Tool description states 'create, or delete hotspot vouchers' — creation is Write (reversible modification of voucher records), while deletion could suggest Destructive; however, guest WiFi vouchers are typically ephemeral access credentials with limited scope…
Attacks that exploit this kind of access
List, create, or delete hotspot vouchers for guest WiFi access. 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_vouchers: 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_vouchers 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_vouchers 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_vouchers. 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_vouchers 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 →