AI agents call whoami to retrieve information from Agentpool without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The 'whoami' tool retrieves identity information about the current user without modifying data or triggering external actions. Despite the empty description reducing confidence slightly, the conventional meaning of 'whoami' across systems indicates a benign read operation with minimal blast radius if misused—an agent learning its own identity causes no harm.
From the tool's definition Tool name 'whoami' is a standard system command that returns the current user identity; description is empty but the name strongly indicates a read-only identity lookup operation.
Attacks that exploit this kind of access
whoami. It is categorised as a Read tool in the Agentpool MCP Server, which means it retrieves data without modifying state.
Register the Agentpool MCP server in PolicyLayer and add a rule for whoami: 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 Agentpool. Nothing to install.
whoami 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 whoami 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 whoami. 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.
whoami is provided by the Agentpool MCP server (zuga-technologies/agentpool-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
whoami is one line of Agentpool's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →