Look up a domain
AI agents call mx_lookup to retrieve information from Domain Security without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
MX lookups are standard DNS queries that retrieve mail exchange records for a domain. This is a read-only operation with no side effects, no data modification, and no ability to execute code or cause harm. The low severity reflects minimal blast radius even if misused—an attacker could only gather information about a domain's mail configuration, which is already publicly queryable via standard DNS tools.
From the tool's definition Tool name 'mx_lookup' and description 'Look up a domain' indicate a query operation that retrieves DNS MX records without modifying data.
Attacks that exploit this kind of access
Look up a domain. It is categorised as a Read tool in the Domain Security MCP Server, which means it retrieves data without modifying state.
Register the Domain Security MCP server in PolicyLayer and add a rule for mx_lookup: 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 Security. Nothing to install.
mx_lookup is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the mx_lookup 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 mx_lookup. 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.
mx_lookup is provided by the Domain Security MCP server (ortamarco/domain-security-mcp-server). 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 →