End a task and clean up the AI model session
AI agents call end_task to permanently remove resources in SystemPrompt Coding Agent — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Ending a task and cleaning up the session destroys the in-progress work state and session context, which cannot be recovered. This is irreversible by nature — once the AI model session is cleaned up, any unsaved in-memory state, partial results, or task context is gone. This qualifies as Destructive rather than Write because 'clean up' implies permanent removal of session data.
From the tool's definition 'End a task and clean up the AI model session' — terminating and cleaning up a session is an irreversible action that destroys the running state of an AI coding task.
Documented attack patterns abuse exactly the kind of access end_task gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SystemPrompt Coding Agent, and nothing reaches the server without passing your rules. This is the rule we recommend for end_task:
{
"version": "1",
"default": "deny",
"hide": [
"end_task"
]
}end_task disappears from the agent's tool list entirely, and any attempt to call it is denied. The rest of the server keeps working.
Free to start. No card required.
End a task and clean up the AI model session. It is categorised as a Destructive tool in the SystemPrompt Coding Agent MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the SystemPrompt Coding Agent MCP server in PolicyLayer and add a rule for end_task: 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 SystemPrompt Coding Agent. Nothing to install.
end_task 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_task 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_task. 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_task is provided by the SystemPrompt Coding Agent MCP server (systempromptio/systemprompt-code-orchestrator). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 SystemPrompt Coding Agent tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
8 SystemPrompt Coding Agent tools catalogued and risk-classified — across an index of 42,500+ MCP servers.