Delete multiple jobs by status or age. Useful for cleaning up failed or old jobs.
AI agents call cortex_cleanup_jobs to permanently remove resources in Cortex — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool performs irreversible deletion of job records at scale. Even though the jobs being deleted may be temporary operational artifacts, the ability to mass-delete by criteria (status, age) without individual confirmation represents a destructive action that cannot be undone.
From the tool's definition Tool name contains 'cleanup_jobs' and description states 'Delete multiple jobs' — the verb 'Delete' indicates irreversible removal of data. The scope ('multiple jobs', 'by status or age') indicates potential for bulk deletion.
Attacks that exploit this kind of access
Delete multiple jobs by status or age. Useful for cleaning up failed or old jobs. It is categorised as a Destructive tool in the Cortex MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Cortex MCP server in PolicyLayer and add a rule for cortex_cleanup_jobs: 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 Cortex. Nothing to install.
cortex_cleanup_jobs 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 cortex_cleanup_jobs 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 cortex_cleanup_jobs. 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.
cortex_cleanup_jobs is provided by the Cortex MCP server (solomonneas/cortex-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 →