Track time entries, projects, workspaces, and clients via the Toggl Track API v9.
Toggl Track 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.togglToggl Track is a time-tracking tool, and this app manages the time entries, projects, workspaces, and clients behind it: starting and stopping a timer, listing and updating past entries, and creating a project to track time against. It is built for workflows that need to record or report on time spent — starting a timer when a task begins, pulling a workspace’s entries for a report, or keeping projects in sync with work tracked elsewhere.
Entries can be listed and filtered, updated after the fact, and deleted, and the workspace and client lists round out the reference data other actions need, such as which workspace a new project or time entry belongs to. Because Toggl scopes most of its API by workspace, actions that create or change data take a workspace as a required parameter rather than guessing at a default.
Three routes to the same 10 actions. The Workflow tab is generated from Toggl Track'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.
time-entry-get-many List the authenticated user's time entries, optionally filtered by date.
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 Toggl Track's real ids.
{
"manifestVersion": "2",
"name": "toggl-example",
"steps": [
{
"id": "client-get-many",
"uses": {
"app": "io.w6w.toggl",
"action": "client-get-many",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"workspaceId": "<workspaceId>"
}
}
]
}client-get-many project-create project-get-many time-entry-get-current time-entry-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 Toggl Track, 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 Toggl Track. 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: "time-entry-start",
payload: {
workspaceId: "<value>",
// description: "<value>",
// projectId: "<value>",
// taskId: "<value>",
// tags: "<value>",
// billable: "<value>",
// start: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action time-entry-start --payload '{"workspaceId":"<value>"}' Give an AI agent Toggl Track — without giving it Toggl Track'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.toggl#client-get-many",
"input": {
"workspaceId": "<workspaceId>"
}
}
}
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 Toggl Track 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.
Toggl Track'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. Toggl Track itself is MIT, and the runtime that executes it is source-available (FSL).
Toggl Track 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.toggl.com, with per-component detail. Unauthenticated and unsigned.