mail_send_draft · Hermes Google MCP: Risk & Policy

WHAT IT DOES

What mail_send_draft does on Hermes Google

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

WHY IT NEEDS A POLICY

Why mail_send_draft needs a policy

Sending a draft email is a reversible write operation—it creates a new sent message in Gmail. While the action cannot be undone perfectly (deletion is always possible but leaves traces), it does not permanently destroy data or move funds. It's more severe than a simple data creation because it involves external communication, but less severe than Destructive or Financial actions.

From the tool's definition Tool name 'mail_send_draft' indicates sending an email draft, which creates/transmits a message. Description is empty, limiting direct evidence, but the name clearly denotes a write operation that modifies Gmail state by converting a draft to a sent message.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mail_send_draft Rate-limited

mail_send_draft 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": {
    "mail_send_draft": {
      "limits": [
        {
          "counter": "mail_send_draft_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 Hermes Google, so you can run agents against it safely.

FAQ

Questions about mail_send_draft

What does the mail_send_draft tool do? +

mail_send_draft. It is categorised as a Write tool in the Hermes 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 mail_send_draft? +

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

What risk level is mail_send_draft? +

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

Can I rate-limit mail_send_draft? +

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

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

mail_send_draft is provided by the Hermes Google MCP server (jimmy-larsson/hermes-google). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.