email_send

THE RISK

Medium Risk

Why email_send needs a policy

Sending an email is an irreversible external communication action. Once sent, it cannot be recalled. The description explicitly labels it as DESTRUCTIVE/IRREVERSIBLE. While it doesn't delete data internally, the real-world blast radius is critical — a misused AI agent could send emails to arbitrary recipients on behalf of the user.

From the tool's definition DESTRUCTIVE / IRREVERSIBLE. Defaults to dry-run preview; pass confirm=true to actually send.

Documented attack patterns abuse exactly the kind of access email_send gives an agent:

POLICY

How to control email_send

PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Email Service, and nothing reaches the server without passing your rules. This is the rule we recommend for email_send:

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "email_send": {
      "limits": [
        {
          "counter": "email_send_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

email_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.

Create a free account and register MCP Email Service — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More MCP Email Service tools

Destructive email_delete DESTRUCTIVE. Defaults to dry-run; pass confirm=true to delete. By default moves to Trash; Destructive email_flag DESTRUCTIVE. Defaults to dry-run; pass confirm=true to apply. Destructive cleanup Rule-based classifier into protected_finance/protected_travel/security/support_case (never Destructive email_move DESTRUCTIVE. Defaults to dry-run; pass confirm=true to apply. Execute digest_run DESTRUCTIVE if confirm=true (sends notifications to Lark/Telegram). Defaults to dry-run pr Write sync_force Refresh the local SQLite cache from IMAP. Synchronous; can take 5-30s for first sync. Subs Write email_mark DESTRUCTIVE. Defaults to dry-run; pass confirm=true to actually flip flags. Read account_list Returns every account known to mailbox: id, email, provider (gmail/qq/163/outlook/...), IM

All 16 MCP Email Service tools →

Write tools on other servers

M-Team MCP Server download_torrent YouTube MCP Server generate_video_title Android Forensics ADB MCP Server combine_reports 0xarchive web3_signup

Go deeper

The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Argument validation → Checking tool call arguments against schema and policy before they run.
Scoped token → Per-person credentials that grant a defined subset of servers and tools.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about email_send

What does the email_send tool do? +

DESTRUCTIVE / IRREVERSIBLE. Defaults to dry-run preview; pass confirm=true to actually send. It is categorised as a Write tool in the MCP Email Service MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on email_send? +

Register the MCP Email Service MCP server in PolicyLayer and add a rule for email_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 MCP Email Service. Nothing to install.

What risk level is email_send? +

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

Can I rate-limit email_send? +

Yes. Add a rate_limit block to the email_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 email_send completely? +

Set action: deny in the PolicyLayer policy for email_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 email_send? +

email_send is provided by the MCP Email Service MCP server (leeguooooo/mailbox). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every MCP Email Service tool call.

Start from MCP Email Service, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →