Delete a vhost from a Simple Hosting instance.
AI agents call gandi_simplehosting_delete_vhost to permanently remove resources in Gandi — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
The tool permanently removes a vhost (virtual host) from a hosting instance, which destroys configuration and access to that virtual host. This is an irreversible data destruction action that fits the Destructive category. Severity is high because deleting a vhost could take down a website or service, though it is scoped to a single vhost rather than an entire instance or organization.
From the tool's definition Tool name contains 'delete' and description states 'Delete a vhost from a Simple Hosting instance' - this is an irreversible deletion operation that cannot be undone.
Attacks that exploit this kind of access
Delete a vhost from a Simple Hosting instance. It is categorised as a Destructive tool in the Gandi MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_simplehosting_delete_vhost: 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 Gandi. Nothing to install.
gandi_simplehosting_delete_vhost 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 gandi_simplehosting_delete_vhost 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 gandi_simplehosting_delete_vhost. 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.
gandi_simplehosting_delete_vhost is provided by the Gandi MCP server (millsymills-com/gandi-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 →