Forcibly end a console session — destructive.
AI agents call end_console_session to permanently remove resources in KVMFleet MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool forcibly terminates an active console session, which is an irreversible action. Once ended, the session cannot be restored, qualifying it as Destructive. Misuse could interrupt legitimate administrative work on KVM devices, potentially causing disruption to critical operations.
From the tool's definition 'Forcibly end a console session — destructive.'
Attacks that exploit this kind of access
Forcibly end a console session — destructive. It is categorised as a Destructive tool in the KVMFleet MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the KVMFleet MCP Server MCP server in PolicyLayer and add a rule for end_console_session: 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 KVMFleet MCP Server. Nothing to install.
end_console_session 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 end_console_session 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 end_console_session. 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.
end_console_session is provided by the KVMFleet MCP Server MCP server (kvmfleet/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 →