delete_gpu_instance
AI agents call delete_gpu_instance to permanently remove resources in Nebulablock — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deletion of cloud compute instances is a destructive, irreversible action that permanently removes infrastructure and associated data. Even though the description is empty, the tool name unambiguously indicates data/resource destruction. Given the context of a cloud infrastructure API (NebulaBlock), deleting a GPU instance would terminate running workloads and is not reversible.
From the tool's definition Tool name is 'delete_gpu_instance' which explicitly indicates deletion/destruction of a GPU instance resource. The verb 'delete' combined with a compute resource indicates irreversible removal.
Attacks that exploit this kind of access
delete_gpu_instance. It is categorised as a Destructive tool in the Nebulablock MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Nebulablock MCP server in PolicyLayer and add a rule for delete_gpu_instance: 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 Nebulablock. Nothing to install.
delete_gpu_instance 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_gpu_instance 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_gpu_instance. 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_gpu_instance is provided by the Nebulablock MCP server (nebula-block-data/nebulablock-mcp-server). 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 →