AI agents call lookup_domain to retrieve information from MCP-Censys without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and summarizes existing domain information from Censys Search API. It has no side effects, does not modify data, execute code, delete records, or move money. The low severity reflects that reconnaissance information, while useful to attackers, is read-only and widely available through legitimate OSINT practices.
From the tool's definition Tool name 'lookup_domain' and description 'Summarize a domain' indicate data retrieval. The parent server description confirms it provides 'reconnaissance' and 'information about hosts, DNS, certificates, and services' without modification or execution…
Documented attack patterns abuse exactly the kind of access lookup_domain gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Censys, and nothing reaches the server without passing your rules. This is the rule we recommend for lookup_domain:
{
"version": "1",
"default": "deny",
"tools": {
"lookup_domain": {}
}
}lookup_domain is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Summarize a domain. It is categorised as a Read tool in the MCP-Censys MCP Server, which means it retrieves data without modifying state.
Register the MCP-Censys MCP server in PolicyLayer and add a rule for lookup_domain: 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 MCP-Censys. Nothing to install.
lookup_domain 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 lookup_domain 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 lookup_domain. 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.
lookup_domain is provided by the MCP-Censys MCP server (nickpending/mcp-censys). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP-Censys, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
5 MCP-Censys tools catalogued and risk-classified — across an index of 43,000+ MCP servers.