Remove all operator-defined tags from a domain.
AI agents call gandi_domain_delete_tags 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.
This tool irreversibly removes all operator-defined tags from a domain. While tags themselves are metadata and not core data, the operation is a bulk destructive action ('remove all') with no indication of reversibility. The blast radius is medium since only metadata/tags are affected, not the domain itself or its DNS records.
From the tool's definition 'delete_tags' and 'Remove all operator-defined tags from a domain'
Attacks that exploit this kind of access
Remove all operator-defined tags from a domain. 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_domain_delete_tags: 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_domain_delete_tags 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_domain_delete_tags 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_domain_delete_tags. 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_domain_delete_tags 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 →