mailtarget_send_email · Mailtarget MCP: Risk & Policy

WHAT IT DOES

What mailtarget_send_email does on Mailtarget

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

WHY IT NEEDS A POLICY

Why mailtarget_send_email needs a policy

This tool sends actual emails, which is a reversible write operation that modifies external state (recipient inboxes). While emails cannot be easily unsent after delivery, the primary action is creating/sending data rather than irreversibly deleting it.

From the tool's definition Tool description states 'Send a transactional email via the Mailtarget Transmission API' and explicitly warns 'Sends real email — use with care.' This is a write operation that creates and delivers real email messages.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mailtarget_send_email Rate-limited

mailtarget_send_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "mailtarget_send_email": {
      "limits": [
        {
          "counter": "mailtarget_send_email_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 Mailtarget, so you can run agents against it safely.

FAQ

Questions about mailtarget_send_email

What does the mailtarget_send_email tool do? +

Send a transactional email via the Mailtarget Transmission API (transmission.mailtarget.co). The from.email domain must be a verified sending domain on the account. Sends real email — use with care. It is categorised as a Write tool in the Mailtarget MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mailtarget_send_email? +

Register the Mailtarget MCP server in PolicyLayer and add a rule for mailtarget_send_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 Mailtarget. Nothing to install.

What risk level is mailtarget_send_email? +

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

Can I rate-limit mailtarget_send_email? +

Yes. Add a rate_limit block to the mailtarget_send_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.

How do I block mailtarget_send_email completely? +

Set action: deny in the PolicyLayer policy for mailtarget_send_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.

What MCP server provides mailtarget_send_email? +

mailtarget_send_email is provided by the Mailtarget MCP server (yopie-org/mailtarget). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.