AI agents use gandi_linkedzone_unlink_domains to create or update resources in Gandi — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gandi environment.
Unlinking domains from a zone modifies the association between domains and DNS zones, which is a reversible write operation (domains can be re-linked). However, it has a high severity because removing DNS zone linkage can cause significant disruption to domain resolution, email delivery, and other services dependent on the DNS configuration.
From the tool's definition Unlink one or more domains from their linked zone
Attacks that exploit this kind of access
Unlink one or more domains from their linked zone. It is categorised as a Write tool in the Gandi MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Gandi MCP server in PolicyLayer and add a rule for gandi_linkedzone_unlink_domains: 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_linkedzone_unlink_domains is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gandi_linkedzone_unlink_domains 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_linkedzone_unlink_domains. 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_linkedzone_unlink_domains 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 →