AI agents invoke local_whois to trigger actions in Net. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
The tool runs a whois lookup locally, meaning it executes a system-level process on the host machine. While whois is a read-only network query, it involves executing a local command rather than simply querying an API, placing it in the Execute category. Misuse risk is medium since it could be used to probe arbitrary hosts/IPs, but the blast radius is limited to network reconnaissance.
From the tool's definition 'Run a whois lookup from the local machine' — executes a local system command/process
Attacks that exploit this kind of access
Run a whois lookup from the local machine. It is categorised as a Execute tool in the Net MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Net MCP server in PolicyLayer and add a rule for local_whois: 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 Net. Nothing to install.
local_whois is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the local_whois 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 local_whois. 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.
local_whois is provided by the Net MCP server (steelcutoatmeal/net-mcp). 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 →