SendGrid
Consume SendGrid API
About
SendGrid ships in the w6w first-party pack. It declares 10 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.sendgrid- Version
- 0.3.3
- Author
- w6w
- Licence
- MIT
- Categories
- Email · Communication
Overview
SendGrid sends email and manages marketing contacts from a workflow — sending mail directly through the API, and creating, reading, updating and deleting the lists a marketing send targets.
Contacts are upserted rather than requiring a workflow to check existence first — a single action creates a contact if it doesn’t exist yet or updates it if it does — and contacts can be fetched individually or listed in bulk to check current state before acting on them.
A fit for sending transactional email straight from a workflow, growing and maintaining a marketing list as people sign up or opt out elsewhere, or keeping SendGrid’s contact data in sync with a CRM.
Build with SendGrid
Three routes to the same 10 actions. The Workflow tab is generated from SendGrid'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 or update a contact
contact-upsert Create a new contact, or update the current one if it already exists (upsert)
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 SendGrid's real ids.
{
"manifestVersion": "2",
"name": "sendgrid-example",
"steps": [
{
"id": "contact-get",
"uses": {
"app": "io.w6w.sendgrid",
"action": "contact-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"by": "<by>"
}
}
]
}Here are some of the things you can do
-
Get a contact
performcontact-get -
Get many contacts
performcontact-get-all -
Create or update a contact
performcontact-upsert -
Create a list
performlist-create -
Get a list
performlist-get
+5 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 SendGrid, 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 SendGrid. 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: "mail-send",
payload: {
// sender: "<value>",
toEmail: "<value>",
subject: "<value>",
// contentValue: "<value>",
dynamicTemplate: "<value>",
templateId: "<value>",
// dynamicTemplateFields: "<value>",
// deliveryOptions: "<value>",
// advancedContent: "<value>",
// additionalFields: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action mail-send --payload '{"toEmail":"<value>","subject":"<value>","dynamicTemplate":"<value>","templateId":"<value>"}'Give an AI agent SendGrid — without giving it SendGrid'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.sendgrid#contact-get",
"input": {
"by": "<by>"
}
}
}
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 SendGrid connections to sign
with, and refuses rather than guesses when the answer is ambiguous.
What the agent gets
Credentials it can't read
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.
A tool surface scoped to the caller
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.
A durable workflow in one call
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.
Health-aware discovery
SendGrid'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. SendGrid itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
SendGrid declares its own checks, so its health is a property of the app rather than something the host guesses at.
SendGrid platform status
Atlassian Statuspage rollup for SendGrid, with per-component detail. Unauthenticated and unsigned.
API rate-limit headroom
Requests remaining on this key, read off the `X-RateLimit-*` headers.