Delete a batch job.
AI agents call delete_batch_job to permanently remove resources in Dataproc MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
This tool removes a batch job, which is an irreversible operation that cannot be undone. Deletion of cloud resources constitutes a destructive action. While the blast radius is constrained to a single batch job (not the entire cluster), unauthorized deletion could disrupt data processing pipelines and lose job history/results.
From the tool's definition Tool name 'delete_batch_job' with description 'Delete a batch job' explicitly indicates irreversible deletion of a batch job resource.
Attacks that exploit this kind of access
Delete a batch job. It is categorised as a Destructive tool in the Dataproc MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Dataproc MCP Server MCP server in PolicyLayer and add a rule for delete_batch_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 Dataproc MCP Server. Nothing to install.
delete_batch_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 delete_batch_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 delete_batch_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.
delete_batch_job is provided by the Dataproc MCP Server MCP server (warrenzhu25/dataproc-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 →