Read and manage Google Tasks: task lists, tasks, completion, reordering, and clearing completed work.
Google Tasks ships in the w6w first-party pack. It declares 13 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.google-tasksGoogle Tasks puts a user’s own task lists and tasks into a workflow — list, create, update and delete task lists; create, update, complete, reorder and delete tasks; and clear out everything already completed in a list. Every write goes through a partial update rather than a full replace, so setting one field never silently clears the others.
The app follows the API’s own quirks rather than papering over them: completing a task is a status change, not a separate endpoint, and reopening one just sets the status back; clearing completed tasks hides them rather than deleting them, so they keep their ids and can still be found later with the right flag; and a due date only ever carries a date, never a time of day, because that is all Google’s Tasks API stores.
Three routes to the same 13 actions. The Workflow tab is generated from Google Tasks'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.
clear-completed-tasks Hide every completed task in a task list. Hidden tasks still exist — list them with `showHidden`.
complete-task Mark a task as completed. Use `update-task` with status `needsAction` to reopen one.
create-task Create a task in a task list, optionally nested under a parent or after a sibling.
list-task-lists List the authenticated user's task lists. Returns one page; pass `pageToken` for the next.
list-tasks List tasks in a task list. Returns one page; pass `pageToken` for the next. All time bounds are RFC 3339 timestamps.
move-task Reposition a task: change its parent, its position among siblings, or move it to another task list.
update-task Update a task's writable fields (patch semantics — omitted fields are left unchanged). Set status to `needsAction` to reopen a completed task.
update-task-list Rename a task list (patch semantics — `title` is its only writable field).
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 Google Tasks's real ids.
{
"manifestVersion": "2",
"name": "google-tasks-example",
"steps": [
{
"id": "clear-completed-tasks",
"uses": {
"app": "io.w6w.google-tasks",
"action": "clear-completed-tasks",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"taskList": "<taskList>"
}
}
]
}clear-completed-tasks complete-task create-task create-task-list get-task +8 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 Google Tasks, 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 Google Tasks. 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: "create-task",
payload: {
taskList: "<value>",
title: "<value>",
// notes: "<value>",
// due: "<value>",
// status: "<value>",
// completed: "<value>",
// parent: "<value>",
// previous: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action create-task --payload '{"taskList":"<value>","title":"<value>"}' Give an AI agent Google Tasks — without giving it Google Tasks'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.google-tasks#clear-completed-tasks",
"input": {
"taskList": "<taskList>"
}
}
}
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 Google Tasks 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.
Google Tasks'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. Google Tasks itself is MIT, and the runtime that executes it is source-available (FSL).
Google Tasks declares its own checks, so its health is a property of the app rather than something the host guesses at.
Open incidents for Google Tasks on the Google Workspace Status Dashboard. Unauthenticated and unsigned.