Cancel a non-terminal task, record a cancel event, notify the other side, and run task.canceled hooks.
AI agents call cancel_task to permanently remove resources in Agent Bus — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a task is an irreversible action — once cancelled, the in-progress work and task state are terminated and cannot be undone. This goes beyond a simple write/update, as it permanently changes the task to a terminal state and triggers cascading hooks and notifications. Misuse by an AI agent could abort legitimate work being performed by other agents.
From the tool's definition Cancel a non-terminal task, record a cancel event, notify the other side, and run task.canceled hooks
Attacks that exploit this kind of access
Cancel a non-terminal task, record a cancel event, notify the other side, and run task.canceled hooks. It is categorised as a Destructive tool in the Agent Bus MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Agent Bus MCP server in PolicyLayer and add a rule for cancel_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 Agent Bus. Nothing to install.
cancel_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 cancel_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 cancel_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.
cancel_task is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →