Manage Brevo (formerly Sendinblue) contacts, senders, attributes, and send transactional emails.
Brevo ships in the w6w first-party pack. It declares 15 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.brevoBrevo (formerly Sendinblue) manages contacts and sends email directly from a workflow — creating, updating, upserting and deleting contacts, and sending both one-off transactional emails and template-based ones without opening Brevo’s dashboard.
Contact attributes — the custom fields a Brevo account defines for segmentation — are managed as their own resource: created, listed and deleted, so a workflow can keep an account’s schema in sync as new fields are needed rather than assuming they already exist. Senders can be created and listed too, covering the identities transactional email is sent from.
A natural fit for turning an external event into an email send — welcoming a new signup, sending a receipt, or upserting a contact’s attributes as their status changes elsewhere in a workflow — while keeping the underlying marketing list Brevo’s own source of truth.
Three routes to the same 15 actions. The Workflow tab is generated from Brevo'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.
create-attribute Create a contact attribute (normal / transactional / category / calculated / global).
send-email Send a transactional email via Brevo (POST /smtp/email). Provide either `htmlContent` or `textContent`.
send-template-email Send a transactional email via an existing Brevo template (POST /smtp/email with `templateId`).
update-attribute Update an existing contact attribute (only category/calculated/global).
upsert-contact Create the contact if it doesn't exist, otherwise update it (sets updateEnabled).
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 Brevo's real ids.
{
"manifestVersion": "2",
"name": "brevo-example",
"steps": [
{
"id": "create-attribute",
"uses": {
"app": "io.w6w.brevo",
"action": "create-attribute",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"category": "<category>",
"name": "<name>"
}
}
]
}create-attribute create-contact create-sender get-contact list-attributes +10 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 Brevo, 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 Brevo. 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: "send-email",
payload: {
sender: "<value>",
to: "<value>",
subject: "<value>",
// htmlContent: "<value>",
// textContent: "<value>",
// cc: "<value>",
// bcc: "<value>",
// replyTo: "<value>",
// attachment: "<value>",
// tags: "<value>",
// headers: "<value>",
// params: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action send-email --payload '{"sender":"<value>","to":"<value>","subject":"<value>"}' Give an AI agent Brevo — without giving it Brevo'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.brevo#create-attribute",
"input": {
"category": "<category>",
"name": "<name>"
}
}
}
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 Brevo 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.
Brevo'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. Brevo itself is MIT, and the runtime that executes it is source-available (FSL).
Brevo declares its own checks, so its health is a property of the app rather than something the host guesses at.
Atlassian Statuspage rollup for status.brevo.com, with per-component detail. Unauthenticated and unsigned.
Requests remaining on this credential, read off the `x-sib-ratelimit-*` headers.