Terminate an active agent session and clean up its resources.
AI agents call kill_agent to permanently remove resources in Agent Link — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Killing an agent session is a destructive, irreversible action. Once terminated, the agent's state, context, and resources are cleaned up and cannot be recovered. This maps clearly to the Destructive category. Severity is high because an AI agent misusing this tool could terminate critical agent workflows mid-execution, potentially causing data loss or disruption of dependent processes.
From the tool's definition 'Terminate an active agent session and clean up its resources' — termination and resource cleanup are irreversible; the agent session is destroyed and cannot be resumed.
Attacks that exploit this kind of access
Terminate an active agent session and clean up its resources. It is categorised as a Destructive tool in the Agent Link MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Link MCP server in PolicyLayer and add a rule for kill_agent: 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 Agent Link. Nothing to install.
kill_agent 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 kill_agent 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 kill_agent. 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.
kill_agent is provided by the Agent Link MCP server (mikusnuz/agent-link-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
kill_agent is one line of Agent Link's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →