MailKite
Get your API key
All guides Agent email

Agent email with Mailgun

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 Mailgun, then shows the same thing the MailKite way, where the agent gets email as native tools over MCP.

What you'll need

  • A Mailgun API key and a verified sending domain.
  • An agent runtime that can call tools (function calling or MCP).
  • For inbound: a public HTTPS endpoint for a Mailgun Route to forward to.

Part 1 — Give your agent email with Mailgun

Mailgun is an email API, not an agent framework, so an agent inbox here means wrapping its messages send API as a tool the model can call, and feeding inbound mail — forwarded by a Route — 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 Mailgun messages endpoint. The request is form-encoded and uses basic auth with api as the username and your key as the password:

send_email.js
// Expose Mailgun's 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: form-encoded POST to the Mailgun messages endpoint,
// basic auth with "api" as the user and your key as the password.
async function runSendEmail({ to, subject, text, html }) {
const domain = process.env.MAILGUN_DOMAIN;
const body = new URLSearchParams({
from: `agent@${domain}`,
to,
subject,
text,
...(html ? { html } : {}),
});
const res = await fetch(`https://api.mailgun.net/v3/${domain}/messages`, {
method: "POST",
headers: {
Authorization: "Basic " + btoa(`api:${process.env.MAILGUN_API_KEY}`),
"Content-Type": "application/x-www-form-urlencoded",
},
body,
});
return res.json();
}

See Send email with Mailgun for the full sending reference.

2. Receive via a Route

Add a Mailgun Route that forwards mail for your agent's address to a webhook. Mailgun POSTs the parsed message as multipart form data, which you hand to the model:

handle-inbound.js
// A Mailgun Route forwards inbound mail to your webhook as multipart form data:
// expression: match_recipient("support@yourdomain.com")
// action: forward("https://yourapp.com/hooks/mailgun")

app.post("/hooks/mailgun", upload.none(), (req, res) => {
// Hand the parsed message to your agent's loop
agent.handle({
from: req.body.sender,
subject: req.body.subject,
body: req.body["body-plain"],
});
res.sendStatus(200);
});

See Mailgun Routes for match expressions and forwarding options. That's an agent inbox on Mailgun: wrap send as a tool, forward inbound through a Route, 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.