gmail_draft_send · Google Workspace MCP: Risk & Policy

WHAT IT DOES

What gmail_draft_send does on Google Workspace

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

WHY IT NEEDS A POLICY

Why gmail_draft_send needs a policy

This tool creates an irreversible side effect by dispatching an email message. While not destructive of existing data, sending email on behalf of a user is a Write action with high severity because: (1) it modifies email state (draft → sent), (2) it triggers external communication that cannot be easily undone, (3) misuse could send unauthorized emails to unintended recipients, impacting reputation and trust.

From the tool's definition Tool name 'gmail_draft_send' and description 'Send an existing draft' indicates the tool commits a draft email to send, which modifies the state of the email (from draft to sent) and triggers external delivery of a message.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

gmail_draft_send Rate-limited

gmail_draft_send 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_draft_send": {
      "limits": [
        {
          "counter": "gmail_draft_send_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 Workspace, so you can run agents against it safely.

FAQ

Questions about gmail_draft_send

What does the gmail_draft_send tool do? +

Send an existing draft. It is categorised as a Write tool in the Google Workspace 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_draft_send? +

Register the Google Workspace MCP server in PolicyLayer and add a rule for gmail_draft_send: 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 Workspace. Nothing to install.

What risk level is gmail_draft_send? +

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

Can I rate-limit gmail_draft_send? +

Yes. Add a rate_limit block to the gmail_draft_send 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_draft_send completely? +

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

gmail_draft_send is provided by the Google Workspace MCP server (rajool/google-workspace-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.