AI agents invoke send-email to trigger actions in SMTP MCP Server. 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.
Sending an email is an external operation with real-world consequences (delivering messages to recipients). It is not merely writing data to a store; it executes an outbound communication action. Misuse could result in spam, phishing, or harassment campaigns, giving it high severity. The broader server context (bulk sending, multiple SMTP configs) amplifies the blast radius.
From the tool's definition "Send an email to one or more recipients" — triggers external email delivery via SMTP
Documented attack patterns abuse exactly the kind of access send-email gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and SMTP MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for send-email:
{
"version": "1",
"default": "deny",
"tools": {
"send-email": {
"limits": [
{
"counter": "send-email_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}send-email 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.
Free to start. No card required.
Send an email to one or more recipients. It is categorised as a Execute tool in the SMTP MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the SMTP MCP Server MCP server in PolicyLayer and add a rule for 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 SMTP MCP Server. Nothing to install.
send-email is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
send-email is provided by the SMTP MCP Server MCP server (samihalawa/mcp-server-smtp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from SMTP MCP Server, 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.
11 SMTP MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.