AI agents call gmail_get_forwarding 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.
This tool retrieves Gmail forwarding configuration, which is a read-only operation that queries current settings without side effects. Although forwarding settings are sensitive, the act of reading them poses minimal risk compared to tools that modify or execute actions. Confidence is moderate (0.85) because the description is empty, but the naming convention strongly suggests a retrieval operation.
From the tool's definition Tool name 'gmail_get_forwarding' indicates retrieval of forwarding settings. The function name follows a GET pattern, suggesting it queries existing configuration rather than modifying it.
Attacks that exploit this kind of access
gmail_get_forwarding. 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_get_forwarding: 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_get_forwarding 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_forwarding 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_forwarding. 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_forwarding is provided by the Mcp Gmail MCP server (@monsoft/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 →