AI agents call dns_lookup to retrieve information from Keel without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
DNS lookup is a read-only operation that retrieves DNS record information about a domain. It does not modify, delete, execute code, or commit financial transactions. The tool simply queries and returns DNS resolution data, which is informational only. The low severity reflects that misuse would primarily enable reconnaissance rather than cause direct harm to systems or data.
From the tool's definition Tool name is 'dns_lookup' and description states it 'Resolve DNS records for a domain using dnspython' — a pure query operation with no side effects.
Attacks that exploit this kind of access
Resolve DNS records for a domain using dnspython. It is categorised as a Read tool in the Keel MCP Server, which means it retrieves data without modifying state.
Register the Keel MCP server in PolicyLayer and add a rule for dns_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 Keel. Nothing to install.
dns_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 dns_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 dns_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.
dns_lookup is provided by the Keel MCP server (seayniclabs/keel). 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 →