gmail_send_message · Google MCP: Risk & Policy

WHAT IT DOES

What gmail_send_message does on Google

AI agents use gmail_send_message 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 gmail_send_message needs a policy

Sending a message modifies data by creating a new artifact in the user's Gmail system. While reversible (messages can be deleted), the severity is high because an AI agent misusing this tool could spam, phish, or send fraudulent messages to arbitrary recipients with significant reputational and security consequences.

From the tool's definition Tool name 'gmail_send_message' and description 'Send a Gmail message' indicate the tool creates and sends a new message, which is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gmail_send_message Rate-limited

gmail_send_message 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": {
    "gmail_send_message": {
      "limits": [
        {
          "counter": "gmail_send_message_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 gmail_send_message

What does the gmail_send_message tool do? +

Send a Gmail message. 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 gmail_send_message? +

Register the Google MCP server in PolicyLayer and add a rule for gmail_send_message: 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 gmail_send_message? +

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

Can I rate-limit gmail_send_message? +

Yes. Add a rate_limit block to the gmail_send_message 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 gmail_send_message completely? +

Set action: deny in the PolicyLayer policy for gmail_send_message. 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 gmail_send_message? +

gmail_send_message 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.