AI agents call google_auth_status to retrieve information from Google 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 to check authentication status and retrieve user information. It has no side effects, does not execute code, does not create or modify data, and does not delete anything. The blast radius of misuse is minimal—an attacker could learn who is authenticated and basic user metadata, but cannot perform actions on calendars or other resources. This is a standard Read classification.
From the tool's definition Tool name 'google_auth_status' and description 'Check Google authentication status and user info' indicate a query operation that retrieves authentication state and user information without modifying data.
Attacks that exploit this kind of access
Check Google authentication status and user info. It is categorised as a Read tool in the Google MCP Server, which means it retrieves data without modifying state.
Register the Google MCP server in PolicyLayer and add a rule for google_auth_status: 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 Google. Nothing to install.
google_auth_status 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 google_auth_status 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 google_auth_status. 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.
google_auth_status is provided by the Google MCP server (robcerda/google-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 →