Send SIGTERM to a running job and mark it cancelled.
AI agents call cancel_job to permanently remove resources in Unlimited — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Cancelling a running job is irreversible — the in-progress work is terminated and the job is permanently marked as cancelled. This cannot be undone, making it Destructive. The blast radius is high because an AI agent could mistakenly cancel legitimate long-running jobs, losing all progress made by those background agents.
From the tool's definition Send SIGTERM to a running job and mark it cancelled
Attacks that exploit this kind of access
Send SIGTERM to a running job and mark it cancelled. It is categorised as a Destructive tool in the Unlimited MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Unlimited MCP server in PolicyLayer and add a rule for cancel_job: 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 Unlimited. Nothing to install.
cancel_job 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_job 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_job. 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_job is provided by the Unlimited MCP server (triumsebas/unlimited-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 →