Create and manage Typeform forms, responses, workspaces, themes and images via the Typeform APIs.
Typeform 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.
io.w6w.typeformTypeform manages forms and reads their responses from a workflow — creating, updating, fetching, listing and deleting forms, so a workflow can provision or retire a form as part of a larger process rather than only reading data from ones built by hand.
Responses can be listed and deleted, which covers pulling in what people submitted and clearing out ones that shouldn’t be kept, such as a deletion request. Workspaces, themes and images can each be listed, giving a workflow the context — which workspace a form lives in, which theme or image assets are available — needed to create a form that matches the rest of an account’s style.
A fit for spinning up forms programmatically, pulling submitted responses into a CRM or spreadsheet, or managing form lifecycle and workspace organization from outside Typeform’s own dashboard.
Three routes to the same 10 actions. The Workflow tab is generated from Typeform'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.
form-get-many List forms in the account, with optional search, workspace filter and paging.
response-get-many Retrieve the responses submitted to a form, with paging and filtering.
workspace-get-many List the workspaces in the account, with optional search and paging.
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 Typeform's real ids.
{
"manifestVersion": "2",
"name": "typeform-example",
"steps": [
{
"id": "form-create",
"uses": {
"app": "io.w6w.typeform",
"action": "form-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"title": "<title>"
}
}
]
}form-create form-get form-get-many form-update image-get-many +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 Typeform, 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 Typeform. 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: "form-create",
payload: {
title: "<value>",
// type: "<value>",
// workspaceHref: "<value>",
// themeHref: "<value>",
// definition: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action form-create --payload '{"title":"<value>"}' Give an AI agent Typeform — without giving it Typeform'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.typeform#form-create",
"input": {
"title": "<title>"
}
}
}
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 Typeform 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.
Typeform'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. Typeform itself is MIT, and the runtime that executes it is source-available (FSL).
Typeform 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.typeform.com, with per-component detail. Unauthenticated and unsigned.