Configure MX records with mail provider template
AI agents use setup_mx to create or update resources in Domain Suite — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Domain Suite environment.
MX records are DNS configurations that control where email for a domain is routed. The 'setup_mx' tool allows creation or modification of these records via mail provider templates. This is a Write operation (reversible modification of domain infrastructure) rather than Execute or Destructive, as MX records can be reconfigured or deleted.
From the tool's definition Tool name 'setup_mx' with description 'Configure MX records with mail provider template' indicates modification of DNS Mail Exchange records.
Attacks that exploit this kind of access
Configure MX records with mail provider template. It is categorised as a Write tool in the Domain Suite MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Domain Suite MCP server in PolicyLayer and add a rule for setup_mx: 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 Domain Suite. Nothing to install.
setup_mx 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 setup_mx 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 setup_mx. 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.
setup_mx is provided by the Domain Suite MCP server (oso95/domain-suite-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 →