AI agents use gmail_send_email to create or update resources in Mcp Gmail — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Gmail environment.
Sending emails is a Write operation—it creates and transmits data with persistent side effects. It is not Destructive (emails can be recalled/unsent in some cases), not Financial (no money moves), and not Execute (it doesn't run arbitrary code). Severity is high because an AI agent misusing this tool could spam users, send phishing emails, impersonate the account holder, or cause reputational damage.
From the tool's definition Tool name 'gmail_send_email' indicates the tool sends emails via Gmail. Combined with the server's Gmail integration and auto-authentication support, this tool creates and transmits new email messages.
Attacks that exploit this kind of access
gmail_send_email. It is categorised as a Write tool in the Mcp Gmail MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Gmail MCP server in PolicyLayer and add a rule for gmail_send_email: 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_send_email is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the gmail_send_email 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_send_email. 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_send_email 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 →