Delete an instance.
AI agents call delete_instance to permanently remove resources in Verda Cloud MCP Server — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
Deleting a cloud instance is an irreversible operation that destroys infrastructure, data, and any running workloads. This cannot be undone without full restoration from backups. The blast radius is critical—an AI agent with accidental or malicious access could destroy production infrastructure, incur data loss, and disrupt operations.
From the tool's definition Tool name 'delete_instance' with description 'Delete an instance' indicates irreversible removal of a cloud GPU instance resource.
Attacks that exploit this kind of access
Delete an instance. It is categorised as a Destructive tool in the Verda Cloud MCP Server MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Verda Cloud MCP Server MCP server in PolicyLayer and add a rule for delete_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 Verda Cloud MCP Server. Nothing to install.
delete_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_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_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_instance is provided by the Verda Cloud MCP Server MCP server (sniper35/verda-cloud-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 →