Delete a batch job. Only works on ended (succeeded/failed/cancelled) jobs.
AI agents call delete_batch to permanently remove resources in Gpal — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool deletes batch job records, which cannot be undone. While the impact is scoped to completed jobs (reducing blast radius compared to unrestricted deletion), it still permanently removes data and historical records. This qualifies as Destructive rather than Write (which covers reversible modifications).
From the tool's definition Tool name 'delete_batch' and description 'Delete a batch job' explicitly indicates irreversible deletion of data (batch job records/artifacts). The constraint 'Only works on ended jobs' does not change the destructive nature—it merely limits scope.
Documented attack patterns abuse exactly the kind of access delete_batch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Gpal, and nothing reaches the server without passing your rules. This is the rule we recommend for delete_batch:
{
"version": "1",
"default": "deny",
"hide": [
"delete_batch"
]
}delete_batch 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.
Delete a batch job. Only works on ended (succeeded/failed/cancelled) jobs. It is categorised as a Destructive tool in the Gpal MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gpal MCP server in PolicyLayer and add a rule for delete_batch: 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 Gpal. Nothing to install.
delete_batch 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 delete_batch 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 delete_batch. 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.
delete_batch is provided by the Gpal MCP server (tobert/gpal). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Gpal, 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.
19 Gpal tools catalogued and risk-classified — across an index of 43,000+ MCP servers.