AI agents call session_info to retrieve information from Wardrowbe without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that returns identity/session information about the current user. It has no capability to modify data, execute commands, delete records, or affect financial systems. The blast radius of misuse is minimal—an AI agent calling this would only learn who is currently authenticated, which is low-risk information disclosure in most contexts.
From the tool's definition Tool name 'session_info' and description 'Return the current authenticated user record (whoami)' indicate a query operation that retrieves information about the authenticated user without modification or side effects.
Attacks that exploit this kind of access
Return the current authenticated user record (whoami). It is categorised as a Read tool in the Wardrowbe MCP Server, which means it retrieves data without modifying state.
Register the Wardrowbe MCP server in PolicyLayer and add a rule for session_info: 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 Wardrowbe. Nothing to install.
session_info 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 session_info 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 session_info. 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.
session_info is provided by the Wardrowbe MCP server (saya6k/mcp-wardrowbe). 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 →