mail_send_message · Mcp Mac MCP: Risk & Policy

WHAT IT DOES

What mail_send_message does on Mcp Mac

AI agents invoke mail_send_message to trigger actions in Mcp Mac. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why mail_send_message needs a policy

This tool triggers an external operation (sending an email) that has real-world irreversible consequences. Once an email is sent, it cannot be unsent. It operates on the most recently created message (likely paired with mail_create_message), meaning an AI agent could compose and send arbitrary emails to arbitrary recipients.

From the tool's definition Send the most recently created message

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mail_send_message Rate-limited

mail_send_message stays usable, but rate-capped — a runaway agent can't fire it dozens of times 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_message": {
      "limits": [
        {
          "counter": "mail_send_message_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Mcp Mac, so you can run agents against it safely.

FAQ

Questions about mail_send_message

What does the mail_send_message tool do? +

Send the most recently created message. It is categorised as a Execute tool in the Mcp Mac MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on mail_send_message? +

Register the Mcp Mac MCP server in PolicyLayer and add a rule for mail_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 Mcp Mac. Nothing to install.

What risk level is mail_send_message? +

mail_send_message is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit mail_send_message? +

Yes. Add a rate_limit block to the mail_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 mail_send_message completely? +

Set action: deny in the PolicyLayer policy for mail_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 mail_send_message? +

mail_send_message is provided by the Mcp Mac MCP server (samicokar/mcp-mac). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.