Force disconnect a client from the network
AI agents invoke disconnect_client to trigger actions in UniFi MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool forces a network disconnection event on a client device, which is an active operation with immediate real-world effects. It is not merely destructive (no data is permanently deleted) but it executes a network management action that can disrupt user connectivity. It falls under Execute as it triggers an external operation on network infrastructure.
From the tool's definition 'Force disconnect a client from the network' — actively triggers an external network operation that disrupts a connected client's session
Attacks that exploit this kind of access
Force disconnect a client from the network. It is categorised as a Execute tool in the UniFi MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the UniFi MCP Server MCP server in PolicyLayer and add a rule for disconnect_client: 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 MCP Server. Nothing to install.
disconnect_client is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the disconnect_client 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 disconnect_client. 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.
disconnect_client is provided by the UniFi MCP Server MCP server (nntkio/unifimcp). 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 →