Block a client
AI agents invoke unifi_block_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.
Blocking a client is a network enforcement action that cuts off a device's connectivity. It is reversible (there is likely an unblock tool), so it does not qualify as Destructive, but it triggers an external operation with significant impact on the affected client, classifying it as Execute. Misuse by an AI agent could deny network access to legitimate users, hence high severity.
From the tool's definition 'Block a client' — triggers an external network operation that denies a client's access to the network
Attacks that exploit this kind of access
Block a client. 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 unifi_block_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.
unifi_block_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 unifi_block_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 unifi_block_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.
unifi_block_client is provided by the UniFi MCP Server MCP server (mjrestivo16/mcp-unifi). 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 →