AI agents call gmail_auth_status to retrieve information from Mcp Gmail without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries and retrieves authentication metadata without modifying any data, executing code, or triggering external operations. It is a read-only status check. Severity is low because disclosure of authentication state information (presence, scope, expiry) poses minimal direct risk and is defensive security information.
From the tool's definition Tool description explicitly states it 'Return[s] the current authentication state' and 'Does NOT expose token values — only presence, scope, and expiry.' This is purely informational retrieval with no side effects.
Attacks that exploit this kind of access
Return the current authentication state. Does NOT expose token values — only presence, scope, and expiry. It is categorised as a Read tool in the Mcp Gmail MCP Server, which means it retrieves data without modifying state.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_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 Mcp Gmail. Nothing to install.
gmail_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 gmail_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 gmail_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.
gmail_auth_status is provided by the Mcp Gmail MCP server (knowledgeislands/mcp-gmail). 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 →