AI agents use google_gmail_draft_email to create or update resources in Google MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Google MCP environment.
This tool creates email drafts but does not send them, making it a Write operation (reversible data creation) rather than Execute or Destructive. However, it carries medium severity because a malicious agent could draft phishing emails, spam, or fraudulent communications at scale, which—while not immediately harmful—represent a significant risk if the drafts are later sent or used to deceive users.
From the tool's definition Tool name is 'google_gmail_draft_email' and description states 'Create a draft email'. The action is creating/composing email content, which is reversible (drafts can be deleted or discarded without sending).
Documented attack patterns abuse exactly the kind of access google_gmail_draft_email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Google MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for google_gmail_draft_email:
{
"version": "1",
"default": "deny",
"tools": {
"google_gmail_draft_email": {
"limits": [
{
"counter": "google_gmail_draft_email_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}google_gmail_draft_email 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.
Free to start. No card required.
Create a draft email. It is categorised as a Write tool in the Google MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Google MCP server in PolicyLayer and add a rule for google_gmail_draft_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 Google MCP. Nothing to install.
google_gmail_draft_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 google_gmail_draft_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 google_gmail_draft_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.
google_gmail_draft_email is provided by the Google MCP server (vakharwalad23/google-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Google MCP, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
35 Google MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.