SimpleTexting
Send SMS and MMS, manage contacts, lists and custom fields, run campaigns, and subscribe webhooks to SimpleTexting's messaging events.
About
SimpleTexting ships in the w6w first-party pack. It declares 27 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
- App id
io.w6w.simpletexting- Version
- 0.1.0
- Author
- w6w
- Licence
- MIT
- Categories
- Communication · Marketing
Overview
SimpleTexting is an SMS marketing and two-way texting platform, and this app covers the messaging surface a workflow actually drives: sending a single SMS or MMS to a contact with a chosen presentation mode, and evaluating a message body first to see what it will cost in credits and whether it fits in one SMS or spills into an extended SMS or an MMS.
Around the send, it manages the audience: contacts (create, look up by phone number or ID, update, delete), the lists those contacts belong to, list membership, and the segments and custom fields an account has defined. It also exposes read-only tenant information (the account’s own email and its sending phone numbers), so a workflow can pick the number to send from rather than hard-coding it.
Campaigns are covered end to end for the immediate case: send a campaign to a set of lists or segments with a message template, list the campaigns an account has sent with filters for type, state, list and date range, and read one campaign’s full state, message template, lists, segments and delivery outcome.
For event-driven workflows, webhooks can be created, listed, updated and deleted, with the platform’s own eight trigger names (incoming and outgoing messages, delivery and non-delivery reports, unsubscribes, conversation open/close, contact phone updates) offered as a multi-select, and an optional per-second delivery rate limit.
Health checks report SimpleTexting’s own status page — anchored on its dedicated API component — alongside the credential check derived from the connection, and state plainly that the vendor publishes no readable quota.
Build with SimpleTexting
Three routes to the same 27 actions. The Workflow tab is generated from SimpleTexting'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.
List Contacts
contact-list List contacts on the account, optionally only those updated since a timestamp.
Add Contact To List
contact-list-add-contact Add one contact to a contact list by phone number or ID.
List Contact Lists
contact-list-list List the account's contact lists, with their membership counts.
Remove Contact From List
contact-list-remove-contact Remove one contact from a contact list by phone number or ID.
List Custom Fields
custom-field-list List the account's custom fields, with their merge tags and length limits.
Evaluate Message
message-evaluate Check what a message body would cost and how it would be sent, without sending it.
Get Account Info
tenant-info-get Read the account's email address — the one endpoint that identifies the tenant.
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 SimpleTexting's real ids.
{
"manifestVersion": "2",
"name": "simpletexting-example",
"steps": [
{
"id": "campaign-get",
"uses": {
"app": "io.w6w.simpletexting",
"action": "campaign-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"campaignId": "<campaignId>"
}
}
]
}Here are some of the things you can do
-
Get Campaign
readcampaign-get -
List Campaigns
searchcampaign-list -
Send Campaign
performcampaign-send -
Create Contact
performcontact-create -
Get Contact
readcontact-get
+22 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 SimpleTexting, 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 SimpleTexting. 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: "campaign-get",
payload: {
campaignId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value);npm install -g @w6w/cliw6w run conn_YOUR_CONNECTION_ID --action campaign-get --payload '{"campaignId":"<value>"}'Give an AI agent SimpleTexting — without giving it SimpleTexting'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.simpletexting#campaign-get",
"input": {
"campaignId": "<campaignId>"
}
}
}
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 SimpleTexting 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
SimpleTexting'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. SimpleTexting itself is MIT, and the runtime that executes it is source-available (FSL).
Health checks
SimpleTexting declares its own checks, so its health is a property of the app rather than something the host guesses at.
SimpleTexting API status
Component status from status.simpletexting.com, anchored on its dedicated API component. The messaging-pipeline components (SMS, MMS, Incoming, Outgoing) and Login are reported alongside it but do not decide the verdict.