Send transactional and templated email, and manage identities, templates, suppression and contacts, in Amazon SES.
Amazon SES ships in the w6w first-party pack. It declares 23 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.sesAmazon SES sends a workflow’s email through your own AWS account — a single transactional message, a stored template rendered with per-message data, or a bulk send of one template to up to 50 recipients, each with its own values. Sends can carry a configuration set and message tags so delivery, bounce and complaint events stay attributable to the workflow that caused them.
Beyond sending, the app covers the account state a sender depends on: registering and inspecting verified email and domain identities (including the DKIM records to publish), keeping stored templates in sync, reading and editing the suppression list that stops mail to bounced or complaining addresses, and managing contact lists and their contacts.
Every request is signed locally with AWS Signature Version 4 against the SES v2 API in the region chosen on the connection, so no AWS SDK is needed. Health checks follow AWS’s per-region SES status and the account’s live 24-hour sending quota, so a workflow can see a sandbox limit or a suspended account before the next send fails.
Three routes to the same 23 actions. The Workflow tab is generated from Amazon SES's own manifest and carries its real ids, so it is copy-pasteable; the Code and CLI examples are the same call for any action on any app, so every app-specific value in them is a blank you fill in.
account-get Read this region's SES account state: sending quota, production access, enforcement and suppression settings.
configuration-set-list List the configuration set names in this region, for use in the send actions.
contact-search List the contacts in a contact list, optionally only those opted in or out.
identity-create Register an email address or domain as a sending identity; SES emails a verification link for an address and returns DKIM tokens for a domain.
identity-delete Delete a sending identity. Mail from that address or domain stops sending immediately.
identity-get Read one sending identity: verification status, DKIM tokens, MAIL FROM and feedback-forwarding settings.
identity-list List the email addresses and domains registered as sending identities in this region.
send-bulk-email Send one stored template to many recipients (up to 50 per call), each with its own replacement data.
send-email Send a simple email (subject plus a text and/or HTML body) through Amazon SES.
send-templated-email Send an email rendered from a stored SES template and a data object.
suppression-delete Remove an address from the account suppression list.
suppression-get Check whether one address is on the suppression list, and why.
suppression-list List addresses on the account suppression list (bounces and complaints SES will no longer send to).
suppression-put Add an address to the account suppression list so SES stops sending to it.
A workflow step names the app and the action, and the editor fills in the
connection when you pick one. This is the Step shape from the
workflow spec, carrying Amazon SES's real ids.
{
"manifestVersion": "2",
"name": "ses-example",
"steps": [
{
"id": "contact-create",
"uses": {
"app": "io.w6w.ses",
"action": "contact-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"contactListName": "<contactListName>",
"emailAddress": "<emailAddress>"
}
}
]
}contact-create account-get configuration-set-list contact-get contact-list-list +18 more actions available
Every app-specific value here is a blank you have to fill in. An
app action is reached through the connection that authenticates it, so the
address is a connection id, not the app id — and connections belong to your account,
so a public page cannot know yours. Create one for Amazon SES, then fill in
the three blanks: conn_YOUR_CONNECTION_ID, the action key, and the
parameters that action declares. The call itself is real — the shape is transcribed
from the studio's own snippet builder, which prints the same kind of blanks — but
nothing in it is specific to Amazon SES. The Workflow tab is where this app's
real ids are.
npm install @w6w/sdkyarn add @w6w/sdkpnpm add @w6w/sdkdeno add npm:@w6w/sdkimport { W6wClient, isActionRun } from "@w6w/sdk";
// Reads W6W_BASE_URL and W6W_TOKEN from the environment when omitted.
const client = new W6wClient();
const envelope = await client.run({
urn: "conn_YOUR_CONNECTION_ID",
action: "contact-create",
payload: {
contactListName: "<value>",
emailAddress: "<value>",
// topicPreferences: "<value>",
// unsubscribeAll: "<value>",
// attributesData: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action contact-create --payload '{"contactListName":"<value>","emailAddress":"<value>"}' Give an AI agent Amazon SES — without giving it Amazon SES's credentials. One MCP endpoint exposes every app, function and workflow the caller is entitled to, as tools it can discover and run. Access is granted per team while we onboard.
One tool call{
"name": "w6w_invoke",
"arguments": {
"ref": "app:io.w6w.ses#contact-create",
"input": {
"contactListName": "<contactListName>",
"emailAddress": "<emailAddress>"
}
}
}
Every tool names its target with a single ref. The
app: form above doesn't name a connection at all — the
host resolves which of the caller's Amazon SES connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
The token is attached host-side, at the moment of the call. It is never a tool argument, never in the model's context, and never in a transcript — so a prompt injection has nothing to exfiltrate.
Tools are derived per end user from what that person has actually connected and is entitled to — not one shared bot identity carrying the union of everyone's access.
Multi-step work runs on the workflow engine and returns a run handle the agent can poll — retries, branching and state survive the conversation that started them.
Amazon SES's declared health checks are on the surface too, so an agent can tell "the vendor is down" from "your credential expired" before it burns a retry on either.
The MCP surface is part of the hosted platform. Amazon SES itself is MIT, and the runtime that executes it is source-available (FSL).
Amazon SES declares its own checks, so its health is a property of the app rather than something the host guesses at.
AWS's public Service Health Dashboard current-events feed, filtered to SES's per-region services. Unauthenticated and unsigned.
24-hour send quota and send rate, read from GET /v2/email/account.