AI agents call dns_propagation 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 propagation checks are informational queries that retrieve DNS record distribution status without modifying systems or data. This is consistent with the network diagnostics purpose of the Keel server. Confidence is reduced due to empty description, but the tool name and sibling context strongly suggest read-only behavior.
From the tool's definition Tool name 'dns_propagation' suggests querying DNS propagation status across nameservers. No description provided, but naming pattern aligns with sibling tools (dns_lookup, reverse_dns) that perform read-only network diagnostics.
Attacks that exploit this kind of access
dns_propagation. 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_propagation: 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_propagation 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_propagation 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_propagation. 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_propagation 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 →