Send SMS/MMS, place and control voice calls, and look up phone numbers via Telnyx.
Telnyx ships in the w6w first-party pack. It declares 6 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.telnyxTelnyx is a programmable voice, messaging and numbers platform, and this app covers the core of each: send an SMS or MMS and look one up by ID, place an outbound Call Control call and hang it up, look up a phone number’s carrier or caller-name data, and list the numbers on the account.
Two things about the surface are worth knowing before using it. Sending a message only queues it — the response’s per-recipient status is queued/sending, not delivered — so a workflow that needs the final outcome should read get-message again or listen on a webhook. Placing a call needs a Call Control Application created once in the Telnyx portal (its ID is the connectionId this app asks for); the call itself is asynchronous, returning a call_control_id before the destination has answered, with that answer arriving later as a webhook this app does not wait for.
Telnyx’s much larger surface — Call Control’s ~40 in-call actions (gather, playback, recording, SIP transfer, AI assistants), WhatsApp/RCS messaging, number ordering/porting, and the Fax, Video and Wireless products — is deliberately out of scope; see the README for the full list of what this app does not cover.
Three routes to the same 6 actions. The Workflow tab is generated from Telnyx'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.
lookup-number Look up carrier and line-type information, or caller name, for a phone number.
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 Telnyx's real ids.
{
"manifestVersion": "2",
"name": "telnyx-example",
"steps": [
{
"id": "get-message",
"uses": {
"app": "io.w6w.telnyx",
"action": "get-message",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"id": "<id>"
}
}
]
}get-message hangup-call list-phone-numbers lookup-number make-call +1 more action 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 Telnyx, 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 Telnyx. 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: "get-message",
payload: {
id: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action get-message --payload '{"id":"<value>"}' Give an AI agent Telnyx — without giving it Telnyx'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.telnyx#get-message",
"input": {
"id": "<id>"
}
}
}
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 Telnyx 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.
Telnyx'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. Telnyx itself is MIT, and the runtime that executes it is source-available (FSL).
Telnyx 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.telnyx.com. Reports the page-level indicator plus the two component names this app can attribute unambiguously (Number Lookup API, Outbound Calling Services) — Messaging has no component of its own, and 'API V1'/'API V2' each repeat twice with no group id to tell the copies apart. Unauthenticated and unsigned.