cancel_agent
Cancel a descendant child agent task. This tool only works for tasks spawned by the current task (descendants).
This record as markdown: /tools/cowork-os/cancel-agent.md
What cancel_agent does on CoWork OS
AI agents call cancel_agent to permanently remove resources in CoWork OS, typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Why cancel_agent is rated Critical
Cancelling an agent task is an irreversible operation — the running task and any in-progress work it has accumulated are terminated and cannot be resumed. This is analogous to killing a process: the state is lost and the action cannot be undone, placing it in the Destructive category.
From the tool's definition Cancel a descendant child agent task
Attacks that exploit this kind of access
The rule that runs cancel_agent safely
PolicyLayer is an MCP gateway: it sits between your AI agents and CoWork OS, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For cancel_agent, this is the rule to start with:
cancel_agent is removed from the agent's tool list entirely, so the agent never calls it. The rest of the server keeps working.
The button opens the PolicyLayer dashboard: create your workspace, connect CoWork OS, apply this rule, and every cancel_agent call is checked against it from then on.
Questions about cancel_agent
Cancel a descendant child agent task. This tool only works for tasks spawned by the current task (descendants). It is categorised as a Destructive tool in the CoWork OS MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the CoWork OS MCP server in PolicyLayer and add a rule for cancel_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 CoWork OS. Nothing to install.
cancel_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 cancel_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 cancel_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.
cancel_agent is provided by the CoWork OS MCP server (CoWork-OS/CoWork-OS). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on CoWork OS, and thousands of servers like it.
Across the catalogue