MailKite
Get your API key
All guides Agent email

Agent email with SendGrid

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

What you'll need

  • A SendGrid API key with Mail Send permission.
  • An agent runtime that can call tools (function calling or MCP).
  • For inbound: a public HTTPS endpoint and an MX record pointed at Inbound Parse.

Part 1 — Give your agent an inbox with SendGrid

SendGrid has no agent inbox out of the box — you assemble one. An agent inbox here is two pieces: a send tool backed by SendGrid's Mail Send API, and an inbound webhook (Inbound Parse) that feeds replies into the agent's loop.

1. Describe the send tool

Give your model a function it can call. Keep the schema small — the address to write to, a subject, and an HTML body:

send_email tool
{
"name": "send_email",
"description": "Send an email from the agent's address.",
"parameters": {
"type": "object",
"properties": {
"to": { "type": "string", "description": "Recipient address" },
"subject": { "type": "string" },
"html": { "type": "string", "description": "HTML body" }
},
"required": ["to", "subject", "html"]
}
}

2. Back it with SendGrid's send API

The tool's implementation POSTs to https://api.sendgrid.com/v3/mail/send with your API key. See Send email with SendGrid for the full request:

send_email.js
// Implementation of the send_email tool — POST to SendGrid's Mail Send API
async function send_email({ to, subject, html }) {
const res = await fetch("https://api.sendgrid.com/v3/mail/send", {
method: "POST",
headers: {
"Authorization": `Bearer ${process.env.SENDGRID_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
personalizations: [{ to: [{ email: to }] }],
from: { email: "agent@yourdomain.com" },
subject,
content: [{ type: "text/html", value: html }],
}),
});
return res.status === 202 ? "sent" : `error ${res.status}`;
}

3. Receive

Inbound mail arrives at your Inbound Parse webhook as multipart/form-data. Parse it and hand the message to your agent:

handle-inbound.js
// SendGrid Inbound Parse POSTs each inbound email as multipart/form-data
// to your webhook. Parse it, then feed it into the agent loop.
app.post("/hooks/sendgrid", upload.none(), (req, res) => {
agent.handle({
from: req.body.from,
subject: req.body.subject,
body: req.body.text,
});
res.sendStatus(200);
});

That's an agent inbox on SendGrid: wrap send as a tool, point Inbound Parse at a 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.