AI agents call subdomain_discover to retrieve information from Idig Dns without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Subdomain discovery is a read-only reconnaissance tool that queries DNS and public certificate logs. While the severity is medium because it can surface exposed infrastructure and development environments (information useful for reconnaissance attacks), the operation itself is non-destructive, non-executable, and retrieves only existing public data. No side effects occur beyond information disclosure.
From the tool's definition Tool description states it "discovers subdomains by probing 75 common names plus crt.sh Certificate Transparency logs" - this is passive reconnaissance that retrieves and queries publicly available information without modifying, executing operations, or…
Attacks that exploit this kind of access
Discover subdomains by probing 75 common names plus crt.sh Certificate Transparency logs. Surfaces exposed dev/staging environments. It is categorised as a Read tool in the Idig Dns MCP Server, which means it retrieves data without modifying state.
Register the Idig Dns MCP server in PolicyLayer and add a rule for subdomain_discover: 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 Idig Dns. Nothing to install.
subdomain_discover 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 subdomain_discover 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 subdomain_discover. 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.
subdomain_discover is provided by the Idig Dns MCP server (https://mcp.softricks.net/sse). 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 →