AI agents call cancelTask to permanently remove resources in Ava — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a task is generally an irreversible operation — once cancelled, the task's progress and state are discarded and cannot be undone. This places it in the Destructive category. Severity is high because misuse by an AI agent could silently abort in-progress work and disrupt team workflows tracked in Slack.
From the tool's definition cancelTask — the tool name indicates cancellation of a task, which is typically an irreversible termination action; description translates to 'Input specification for accepting task cancellation'
Documented attack patterns abuse exactly the kind of access cancelTask gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ava, and nothing reaches the server without passing your rules. This is the rule we recommend for cancelTask:
{
"version": "1",
"default": "deny",
"hide": [
"cancelTask"
]
}cancelTask 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.
タスク中止を受け付けるための入力仕様。. It is categorised as a Destructive tool in the Ava MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ava MCP server in PolicyLayer and add a rule for cancelTask: 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 Ava. Nothing to install.
cancelTask 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 cancelTask 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 cancelTask. 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.
cancelTask is provided by the Ava MCP server (yutakobayashidev/ava). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ava, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
10 Ava tools catalogued and risk-classified — across an index of 43,000+ MCP servers.