Delete a network
AI agents call unifi_delete_network to permanently remove resources in UniFi Network MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a network is an irreversible operation that removes network configuration and potentially impacts all devices and clients connected to that network. This falls squarely into the Destructive category as the action cannot be undone and has significant blast radius if triggered maliciously or by mistake.
From the tool's definition Tool name is 'unifi_delete_network' with description 'Delete a network'. The verb 'Delete' is explicitly destructive and irreversible.
Attacks that exploit this kind of access
Delete a network. It is categorised as a Destructive tool in the UniFi Network MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the UniFi Network MCP Server MCP server in PolicyLayer and add a rule for unifi_delete_network: 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 Network MCP Server. Nothing to install.
unifi_delete_network is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the unifi_delete_network 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 unifi_delete_network. 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.
unifi_delete_network is provided by the UniFi Network MCP Server MCP server (ruashots/unifi-network-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 →