AI agents call dns_lookups to retrieve information from Arkime without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs read-only network traffic analysis by searching and filtering captured DNS query records. It extracts information from existing packet capture data without creating, modifying, or deleting any records. The filtering capability does not alter the underlying data.
From the tool's definition Tool description explicitly states 'Search DNS queries captured in network traffic. Filter by domain name pattern' — a query/search operation that retrieves historical DNS data with no modification or side effects.
Attacks that exploit this kind of access
Search DNS queries captured in network traffic. Filter by domain name pattern. It is categorised as a Read tool in the Arkime MCP Server, which means it retrieves data without modifying state.
Register the Arkime MCP server in PolicyLayer and add a rule for dns_lookups: 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 Arkime. Nothing to install.
dns_lookups 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 dns_lookups 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 dns_lookups. 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.
dns_lookups is provided by the Arkime MCP server (swannman/arkime-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 →