AI agents call whois to retrieve information from Agent Bus without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a simple discovery/query operation that retrieves registration information about connected agents. It has no side effects, does not execute code, modify state, or delete data. The blast radius of misuse is minimal—an agent learning what other agents are available and their capabilities poses no direct harm in a collaborative local environment.
From the tool's definition Tool 'whois' explicitly 'lists' agents and metadata (capabilities, timestamps) with no modification or execution capability described.
Risk signalsBulk/mass operation — affects multiple targets
Attacks that exploit this kind of access
List every agent currently registered on the bus along with capabilities and last-seen timestamps. It is categorised as a Read tool in the Agent Bus MCP Server, which means it retrieves data without modifying state.
Register the Agent Bus MCP server in PolicyLayer and add a rule for 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 Agent Bus. Nothing to install.
whois 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 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 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.
whois is provided by the Agent Bus MCP server (mustaphasteph/agent-bus). 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 →