Manage contacts, conversations, and messages across WhatsApp, SMS, and other channels via the respond.io Developer API.
respond.io ships in the w6w first-party pack. It declares 28 actions, 1 health check, and the host runs its code in a sandbox that never sees the credential.
io.w6w.respondiorespond.io unifies WhatsApp, SMS, Messenger, Instagram, email and other channels into one contact-and-conversation inbox. This app covers the respond.io Developer API v2’s five areas: Contacts (create/read/update/delete, upsert, merge, tag, list with field/tag/lifecycle filters), Conversations (assign, open/close), Messaging (send any of the six documented message shapes — text, attachment, WhatsApp template, email, quick reply, custom payload — and read message history), Comments (internal notes on a contact), and Space (workspace users, custom fields, closing notes, channels, WhatsApp templates, and tags).
There is no OAuth surface for third-party apps: a personal API access token, minted per-workspace under Settings > Integrations > Developer API, is the entire authentication story.
Three routes to the same 28 actions. The Workflow tab is generated from respond.io'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.
contact-create Create a new contact. Prefer Create Or Update Contact for a safe-to-retry upsert.
contact-create-or-update Create the contact if it doesn't exist yet, or update it if it does.
contact-list List contacts, optionally filtered by field, tag, or lifecycle conditions.
contact-list-channels List the channels a specific contact has been reached through.
contact-merge Merge two contacts into one, optionally setting field values on the survivor.
conversation-update-status Open or close a contact's conversation, optionally with a closing note.
space-channel-template-list List the WhatsApp message templates approved for one channel.
space-closing-note-list List this workspace's conversation-closing-note categories.
space-tag-update Rename or restyle a workspace tag, addressed by its current name.
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 respond.io's real ids.
{
"manifestVersion": "2",
"name": "respondio-example",
"steps": [
{
"id": "comment-create",
"uses": {
"app": "io.w6w.respondio",
"action": "comment-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"identifier": "<identifier>",
"text": "<text>"
}
}
]
}comment-create contact-add-tags contact-create contact-create-or-update contact-get +23 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 respond.io, 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 respond.io. 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: "comment-create",
payload: {
identifier: "<value>",
text: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action comment-create --payload '{"identifier":"<value>","text":"<value>"}' Give an AI agent respond.io — without giving it respond.io'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.respondio#comment-create",
"input": {
"identifier": "<identifier>",
"text": "<text>"
}
}
}
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 respond.io 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.
respond.io'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. respond.io itself is MIT, and the runtime that executes it is source-available (FSL).
respond.io declares its own checks, so its health is a property of the app rather than something the host guesses at.