whoislookup
AI agents call whoislookup to retrieve information from IR Toolshed MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
WHOIS lookup is a read-only operation that retrieves publicly available domain and IP registration information. It has no side effects, does not modify data, and does not execute arbitrary code. While it could support reconnaissance, the risk is minimal because WHOIS data is public. Confidence is high due to explicit mention in the server description despite the empty tool description.
From the tool's definition Tool is named 'whoislookup' and resides on a server explicitly described as providing 'network analysis tools for security professionals' including 'ASN lookups, DNS analysis, WHOIS retrieval, and IP geolocation'.
Attacks that exploit this kind of access
whoislookup. It is categorised as a Read tool in the IR Toolshed MCP Server MCP Server, which means it retrieves data without modifying state.
Register the IR Toolshed MCP Server MCP server in PolicyLayer and add a rule for whoislookup: 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 IR Toolshed MCP Server. Nothing to install.
whoislookup 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 whoislookup 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 whoislookup. 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.
whoislookup is provided by the IR Toolshed MCP Server MCP server (rossja/irtoolshed-mcp-server). 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 →