MailKite
Get your API key
All guides Agent email

Agent email with Resend

Give an AI agent its own inbox and it can hold a real email conversation — field a support request, follow up on a thread, confirm a booking. This guide sets that up with Resend, then shows the same thing the MailKite way, where the agent gets email as native tools over MCP.

What you'll need

  • A Resend API key (re_...) and a verified sending domain.
  • An agent runtime that can call tools (function calling or MCP).
  • For inbound: a public HTTPS endpoint for Resend's webhook to POST to.

Part 1 — Give your agent email with Resend

Resend is an email API, not an agent framework, so an agent inbox here means wrapping its emails send API as a tool the model can call, and feeding inbound mail — delivered by a signed webhook — back into the agent's loop.

1. Wrap send as a tool

Define a send_email tool and back it with a POST to the Resend emails endpoint. The request is JSON and authed with a Bearer key:

send_email.js
// Expose Resend's emails send API as a tool your agent can call
const send_email = {
name: "send_email",
description: "Send an email on behalf of the agent",
parameters: {
type: "object",
properties: {
to: { type: "string" },
subject: { type: "string" },
text: { type: "string" },
html: { type: "string" },
},
required: ["to", "subject", "text"],
},
};

// Implementation: a JSON POST to the Resend emails endpoint,
// authed with a Bearer key.
async function runSendEmail({ to, subject, text, html }) {
const res = await fetch("https://api.resend.com/emails", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.RESEND_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
from: "agent@yourdomain.com",
to,
subject,
text,
...(html ? { html } : {}),
}),
});
return res.json();
}

See Send email with Resend for the full sending reference.

2. Receive via a signed webhook

Resend POSTs an email.received event to your webhook, signed with Svix. Verify the signature, then hand the message to the model — the payload is metadata, so fetch the full body with a follow-up API call:

handle-inbound.js
// Resend POSTs an email.received event to your webhook, signed with Svix.
// The payload is metadata — verify it, then fetch the full body by id.
import { Webhook } from "svix";

app.post("/hooks/resend", (req, res) => {
const wh = new Webhook(process.env.RESEND_WEBHOOK_SECRET);
const evt = wh.verify(req.rawBody, req.headers); // throws if the signature is bad

if (evt.type === "email.received") {
// Hand it to your agent's loop
agent.handle({
from: evt.data.from,
subject: evt.data.subject,
emailId: evt.data.email_id, // fetch the full body with a follow-up API call
});
}
res.sendStatus(200);
});

See Resend inbound for signature verification and payload details. That's an agent inbox on Resend: wrap send as a tool, verify the inbound webhook, and let your agent run the conversation.

Part 2 — The same, the MailKite way

MailKite is MCP-native, so your agent doesn't call a REST API you wrapped by hand — it speaks MCP and gets email as first-class tools. Connect the server once and the same send-and-reply loop is a few tool calls.

1. Connect the MCP server

Add the hosted server. On the first connect it signs you in over OAuth in the browser — no key to copy — or pass your account key for headless runs:

connect
# Hosted MCP server — OAuth in the browser on first connect, no key to copy
claude mcp add --transport http mailkite https://mcp.mailkite.dev/mcp

# Headless / CI — pass your account key instead of the browser flow
claude mcp add --transport http mailkite https://mcp.mailkite.dev/mcp \
--header "Authorization: Bearer mk_live_..."

Any MCP client — Cursor, Claude Desktop, Cline, Zed — takes the same URL:

mcp config
{
"mcpServers": {
"mailkite": { "url": "https://mcp.mailkite.dev/mcp" }
}
}

2. Send from your agent

The agent calls mailkite_send over any verified domain — HTML, text, cc/bcc, attachments, and in-thread replies. Pick AI in the card for the agent's view, or any language to make the same send from your own code:

send
import { MailKite } from "mailkite";

const mk = new MailKite(process.env.MAILKITE_API_KEY);

const { id, status } = await mk.send({
from: "hello@myapp.ai",
to: "ada@example.com",
subject: "Your invoice #1042",
html: "<p>Thanks! Receipt attached.</p>",
});
Install Docs →
response
202 Accepted
{ "id": "msg_2Hk9…", "status": "queued" }

3. Receive — or hand the whole inbox to the agent

Every address on the domain is receivable. The agent can read inbound with its own tools, or you turn an address into an inbox agent with one route — the model reads and replies on its own:

create the agent route
import { MailKite } from "mailkite";

const mk = new MailKite(process.env.MAILKITE_API_KEY);

// One route turns an address into an AI inbox agent — the prompt
// is the program, and unresolved mail escalates to a human.
await mk.createRoute({
match: "support@myapp.ai",
action: "agent",
agentPrompt:
"Answer billing and account questions for myapp.ai. Reply in-thread. " +
"Escalate anything you can't resolve to humans@myapp.ai.",
agentForwardTo: ["humans@myapp.ai"],
});
Install Docs →
read inbound
// Or read inbound yourself — the agent has tools for it
mailkite_list_messages({ limit: 20 }) // newest first
mailkite_get_message({ id: "msg_2Hk9…" }) // full body, headers, attachment links

Same key manages the domain too — mailkite_create_domain, mailkite_verify_domain — so the agent can provision its own inbox end to end. See Connect your agent for the full tool list.

A little about MailKite

MailKite is programmable email for developers and AI agents. Connect the MCP server once and your agent can send over a verified domain, read its inbound as clean JSON, spin up new inboxes, manage domains, and become an inbox agent that answers mail on its own — all as native tools, no REST wrapper to maintain. It works the same over the SDKs, the CLI, or raw HTTP, and agent inboxes are on the free tier.

Next: Connect your agent for every MCP tool, or Set up your agent's email to go from zero to a working inbox.