Search for subdomains of a given domain.
AI agents call search_subdomains to retrieve information from Dnsdumpster without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation that retrieves DNS subdomain data without side effects. Severity is medium rather than low because DNS reconnaissance can enable follow-on attacks or unauthorized discovery of infrastructure, but the tool itself is non-destructive and information-disclosure only.
From the tool's definition Tool performs DNS reconnaissance by searching for subdomains of a domain. The description states it 'Search[es] for subdomains' with no mention of modifications, deletions, or state changes.
Attacks that exploit this kind of access
Search for subdomains of a given domain. It is categorised as a Read tool in the Dnsdumpster MCP Server, which means it retrieves data without modifying state.
Register the Dnsdumpster MCP server in PolicyLayer and add a rule for search_subdomains: 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 Dnsdumpster. Nothing to install.
search_subdomains 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 search_subdomains 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 search_subdomains. 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.
search_subdomains is provided by the Dnsdumpster MCP server (maxweeden/mcp-dnsdumpster). 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 →