smart_send_email_unsafe · Google MCP: Risk & Policy

WHAT IT DOES

What smart_send_email_unsafe does on Google

AI agents use smart_send_email_unsafe to create or update resources in Google — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google environment.

WHY IT NEEDS A POLICY

Why smart_send_email_unsafe needs a policy

This tool creates and sends emails, which is a Write operation (creates new data/messages). It rates 'high' severity rather than 'critical' because while emails can be problematic if sent maliciously, they are not inherently destructive (can be recalled/deleted by recipient) nor financial in nature. The 'unsafe' designation and lack of confirmation requirement elevates it above standard Write operations.

From the tool's definition Tool name contains 'send_email' and description states 'Send email immediately without confirmation'. The ⚠️ UNSAFE warning flag and explicit mention of sending 'immediately without confirmation' indicates the tool performs irreversible communication actions.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

smart_send_email_unsafe Rate-limited

smart_send_email_unsafe stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "smart_send_email_unsafe": {
      "limits": [
        {
          "counter": "smart_send_email_unsafe_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Google, so you can run agents against it safely.

FAQ

Questions about smart_send_email_unsafe

What does the smart_send_email_unsafe tool do? +

⚠️ UNSAFE: Send email immediately without confirmation (use names or emails). It is categorised as a Write tool in the Google MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on smart_send_email_unsafe? +

Register the Google MCP server in PolicyLayer and add a rule for smart_send_email_unsafe: 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.

What risk level is smart_send_email_unsafe? +

smart_send_email_unsafe is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit smart_send_email_unsafe? +

Yes. Add a rate_limit block to the smart_send_email_unsafe 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.

How do I block smart_send_email_unsafe completely? +

Set action: deny in the PolicyLayer policy for smart_send_email_unsafe. 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.

What MCP server provides smart_send_email_unsafe? +

smart_send_email_unsafe 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.