Bulk-cancel every task in the queue that is still cancellable (status
AI agents call cancel_all to permanently remove resources in Ebb Ai — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling all queued tasks is an irreversible action that destroys pending work state at scale. While not deleting data from permanent storage, it cancels scheduled executions and removes task entries from the queue, which cannot be undone (recovery requires manual rescheduling). This warrants Destructive classification.
From the tool's definition Tool name 'cancel_all' combined with description 'Bulk-cancel every task in the queue that is still cancellable' indicates irreversible deletion of multiple queued tasks.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
Bulk-cancel every task in the queue that is still cancellable (status. It is categorised as a Destructive tool in the Ebb Ai MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Ebb Ai MCP server in PolicyLayer and add a rule for cancel_all: 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 Ebb Ai. Nothing to install.
cancel_all 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_all 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_all. 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_all is provided by the Ebb Ai MCP server (vitalini/ebb-ai). 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 →