Track time entries, projects, clients, and workspaces via the Clockify API v1.
Clockify 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.clockifyClockify tracks time from inside a workflow — creating a time entry the moment work starts, and updating it with an end time to close it out, the same start/stop pattern Clockify’s own API is built around rather than a dedicated timer endpoint.
Projects and clients are manageable too: projects can be listed, fetched, created and deleted, and clients and workspaces can be listed to keep entries pointed at the right place without hardcoding an id. That makes it straightforward to turn an external trigger — a ticket picked up, a calendar event starting — into a running time entry, and a completion event into a closed one, with reporting staying inside Clockify itself.
Three routes to the same 10 actions. The Workflow tab is generated from Clockify'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-update Update a time entry — often used to set `end` and stop a running timer.
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 Clockify's real ids.
{
"manifestVersion": "2",
"name": "clockify-example",
"steps": [
{
"id": "client-list",
"uses": {
"app": "io.w6w.clockify",
"action": "client-list",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"workspaceId": "<workspaceId>"
}
}
]
}client-list project-create project-get project-list time-entry-create +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 Clockify, 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 Clockify. 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-create",
payload: {
workspaceId: "<value>",
start: "<value>",
// end: "<value>",
// description: "<value>",
// projectId: "<value>",
// taskId: "<value>",
// tagIds: "<value>",
// billable: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action time-entry-create --payload '{"workspaceId":"<value>","start":"<value>"}' Give an AI agent Clockify — without giving it Clockify'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.clockify#client-list",
"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 Clockify 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.
Clockify'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. Clockify itself is MIT, and the runtime that executes it is source-available (FSL).
Clockify declares its own checks, so its health is a property of the app rather than something the host guesses at.
No machine-readable status feed was found for Clockify as of 2026-08-01 (status.clockify.me/api/v2/summary.json 404s), so this app declares the absence rather than guessing at an undocumented endpoint.