Manage Qualtrics surveys, XM Directory contacts and response exports.
Qualtrics 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.qualtricsQualtrics is a survey and experience-management (XM) platform. Its REST API v3 is datacenter-sharded: every account lives on one of many regional hosts (iad1.qualtrics.com, fra1.qualtrics.com, syd1.qualtrics.com, …), and a connection records which one it belongs to.
This app covers the survey-and-collect path an automation actually drives. Surveys can be listed and fetched; XM Directory contact pools, mailing lists and their contacts can be read; distributions can be listed per survey; and the three-beat response-export flow — start a job, poll its progress, download the finished file — is modelled end to end.
Libraries, account users, the current organization and event subscriptions round out the administrative surface. Health checks track Qualtrics’ own status page (scoped to the API component, not the page-level roll-up), and the credential check probes whoami, which returns the caller’s own profile and never the API token itself.
A fit for syncing survey responses into a warehouse or CRM, keeping contact pools aligned with another system, or kicking off an export on a schedule without a person logging in.
Three routes to the same 15 actions. The Workflow tab is generated from Qualtrics'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.
event-subscription-list List the account's event subscriptions (webhook registrations).
response-export-file-get Download a completed response export, base64-encoded.
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 Qualtrics's real ids.
{
"manifestVersion": "2",
"name": "qualtrics-example",
"steps": [
{
"id": "directory-contact-get",
"uses": {
"app": "io.w6w.qualtrics",
"action": "directory-contact-get",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"directoryId": "<directoryId>",
"contactId": "<contactId>"
}
}
]
}directory-contact-get directory-contact-list directory-list distribution-list event-subscription-list +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 Qualtrics, 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 Qualtrics. 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: "directory-contact-get",
payload: {
directoryId: "<value>",
contactId: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action directory-contact-get --payload '{"directoryId":"<value>","contactId":"<value>"}' Give an AI agent Qualtrics — without giving it Qualtrics'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.qualtrics#directory-contact-get",
"input": {
"directoryId": "<directoryId>",
"contactId": "<contactId>"
}
}
}
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 Qualtrics 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.
Qualtrics'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. Qualtrics itself is MIT, and the runtime that executes it is source-available (FSL).
Qualtrics declares its own checks, so its health is a property of the app rather than something the host guesses at.
The `API / Developer Platform` component of status.qualtrics.com, read from its Statuspage summary API. The page's other components (Survey Taking, Logins, Email, …) are UI and delivery surfaces that say nothing about the REST API.
Declared absent: Qualtrics publishes no rate-limit response headers and no endpoint that states an allowance.