Revoke (cancel) a task.
AI agents call revoke_task to permanently remove resources in Celery MCP — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Revoking a task is an irreversible action that terminates job execution and cannot be undone. While not deleting data directly, it permanently cancels work in progress—analogous to an irreversible state change. The high severity reflects that an AI agent could disrupt critical business processes by revoking production tasks without authorization.
From the tool's definition Tool name 'revoke_task' with description 'Revoke (cancel) a task' indicates irreversible cancellation of an asynchronous job. Once revoked, a task's execution cannot be resumed or recovered.
Attacks that exploit this kind of access
Revoke (cancel) a task. It is categorised as a Destructive tool in the Celery MCP MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Celery MCP server in PolicyLayer and add a rule for revoke_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 Celery MCP. Nothing to install.
revoke_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 revoke_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 revoke_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.
revoke_task is provided by the Celery MCP server (joeyrubas/celery-mcp). 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 →