AI agents use gandi_livedns_update_domain 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.
This tool modifies DNS zone settings, which is a reversible write operation but can have severe consequences if misconfigured. Changing DNS settings could redirect traffic, break email delivery, or disrupt services. The blast radius is high because incorrect DNS updates affect all services dependent on that domain.
From the tool's definition The tool name explicitly includes 'update' and the description states it will 'Update LiveDNS zone settings.' This indicates modification of existing DNS configuration data.
Attacks that exploit this kind of access
Update LiveDNS zone settings. 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_livedns_update_domain: 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_livedns_update_domain 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_livedns_update_domain 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_livedns_update_domain. 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_livedns_update_domain 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 →