AI agents call gmail_get_profile 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 only retrieves data (the authenticated user's email address) with no capability to modify, delete, or execute operations. It is a simple query that returns profile metadata. The severity is low because exposure of one's own email address has minimal security impact in most contexts.
From the tool's definition Tool name 'gmail_get_profile' and description 'Returns the email address of the currently authenticated Gmail user' indicate a read-only operation that retrieves user profile information without modification or side effects.
Attacks that exploit this kind of access
Returns the email address of the currently authenticated Gmail user. 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 gmail_get_profile: 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.
gmail_get_profile 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 gmail_get_profile 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 gmail_get_profile. 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.
gmail_get_profile is provided by the Google MCP server (psckeithw/mcp-google). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
gmail_get_profile is one line of Google'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 →