AI agents use manage_device 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.
This tool creates or modifies data reversibly by changing device properties like names. While it alters state, the changes are non-destructive and can be undone by renaming again. It does not delete data (Destructive), execute arbitrary commands (Execute), or involve financial transactions (Financial).
From the tool's definition Tool description states 'Update properties of an adopted device — primarily for renaming.' The verb 'Update' combined with 'renaming' indicates modification of device metadata without deletion or irreversible changes.
Attacks that exploit this kind of access
Update properties of an adopted device — primarily for renaming. 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_device: 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_device 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_device 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_device. 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_device 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 →