Track time entries, projects, tasks, clients, and users via the Harvest API v2.
Harvest ships in the w6w first-party pack. It declares 11 actions, 2 health checks, and the host runs its code in a sandbox that never sees the credential.
io.w6w.harvestHarvest tracks time entries, projects, tasks, clients and users through Harvest’s own API v2, giving a workflow the same time-tracking primitives as the product itself. Time entries can be created, read, updated and deleted, and Harvest’s own timer controls are used directly to start, stop and restart a running entry rather than approximating them with plain create calls.
Every request carries both a token and an explicit account id, since a single Harvest credential can reach more than one account — connecting confirms the id actually resolves to a real Harvest account before it’s used anywhere else. Both a personal access token and OAuth2 are supported, covering unattended automation and interactive sign-in alike.
Billing and CRM-adjacent surfaces — invoices, estimates, expenses, contacts and companies — are left out of this first pass; the actions here stay focused on the time-tracking data the API’s own name promises.
Three routes to the same 11 actions. The Workflow tab is generated from Harvest'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.
project-get-many List projects, optionally filtered by active status, client, or update time.
time-entry-create Create a time entry — by duration, by start/end time, or (omitting both) start a running timer.
time-entry-get-many List time entries, optionally filtered by user, client, project, task, or 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 Harvest's real ids.
{
"manifestVersion": "2",
"name": "harvest-example",
"steps": [
{
"id": "time-entry-create",
"uses": {
"app": "io.w6w.harvest",
"action": "time-entry-create",
"connection": "conn_YOUR_CONNECTION_ID"
},
"with": {
"projectId": "<projectId>",
"taskId": "<taskId>",
"spentDate": "<spentDate>"
}
}
]
}time-entry-create client-get-many project-get-many task-get-many time-entry-get +6 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 Harvest, 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 Harvest. 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: {
projectId: "<value>",
taskId: "<value>",
spentDate: "<value>",
// userId: "<value>",
// hours: "<value>",
// startedTime: "<value>",
// endedTime: "<value>",
// notes: "<value>",
},
});
if (isActionRun(envelope)) console.log(envelope.value); npm install -g @w6w/cli w6w run conn_YOUR_CONNECTION_ID --action time-entry-create --payload '{"projectId":"<value>","taskId":"<value>","spentDate":"<value>"}' Give an AI agent Harvest — without giving it Harvest'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.harvest#time-entry-create",
"input": {
"projectId": "<projectId>",
"taskId": "<taskId>",
"spentDate": "<spentDate>"
}
}
}
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 Harvest 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.
Harvest'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. Harvest itself is MIT, and the runtime that executes it is source-available (FSL).
Harvest declares its own checks, so its health is a property of the app rather than something the host guesses at.
Atlassian Statuspage rollup for www.harveststatus.com, with per-component detail. Unauthenticated and unsigned.