Tasks, lists, folders, comments, and time tracking via the ClickUp API.
ClickUp ships in the w6w first-party pack. It declares 12 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.clickupClickUp organizes work as tasks nested under lists, which sit under folders or spaces, and this app follows that same shape: create, read, update and delete tasks; list and create the lists and folders around them; add and read comments; and log or list time entries.
Because a ClickUp resource is always addressed through its parent — a task through its list, a time entry through its team — every action here takes the relevant parent id and builds the right nested request rather than pretending ClickUp’s resources are flat. Dates and durations are handled in ClickUp’s own encoding automatically, so a workflow can pass ordinary datetimes and minutes.
This app is aimed at the everyday task-management loop: creating and updating work, tracking time against it, and keeping comments and structure in sync with whatever triggered the workflow — not at ClickUp’s broader space or workspace administration.
Three routes to the same 12 actions. The Workflow tab is generated from ClickUp'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.
list-create Create a list inside a folder, or a folderless list directly in a space. Provide a Folder ID or a Space ID.
list-get-many List the lists in a folder, or the folderless lists in a space. Provide a Folder ID or a Space ID.
time-entry-get-many List time entries in a workspace (team) within an optional date window.
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 ClickUp's real ids.
{
"manifestVersion": "2",
"name": "clickup-example",
"steps": [
{
"id": "comment-create",
"uses": {
"app": "io.w6w.clickup",
"action": "comment-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"commentOn": "<commentOn>",
"id": "<id>",
"commentText": "<commentText>"
}
}
]
}comment-create comment-get-many folder-get-many list-create list-get-many +7 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 ClickUp, 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 ClickUp. 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: "task-create",
payload: {
listId: "<value>",
name: "<value>",
// content: "<value>",
// assignees: "<value>",
// tags: "<value>",
// status: "<value>",
// priority: "<value>",
// dueDate: "<value>",
// startDate: "<value>",
// parent: "<value>",
// notifyAll: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action task-create --payload '{"listId":"<value>","name":"<value>"}' Give an AI agent ClickUp — without giving it ClickUp'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.clickup#comment-create",
"input": {
"commentOn": "<commentOn>",
"id": "<id>",
"commentText": "<commentText>"
}
}
}
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 ClickUp 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.
ClickUp'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. ClickUp itself is MIT, and the runtime that executes it is source-available (FSL).
ClickUp declares its own checks, so its health is a property of the app rather than something the host guesses at.
Status.io rollup for status.clickup.com, with per-service detail. Unauthenticated and unsigned.
Per-minute request allowance remaining, read off the response headers.