Skip to main content
Productive is a branded card in the Integrations gallery (categories Productivity and Time & Billing) — Productive’s own hosted MCP server, with the address and authentication already fixed by the card. Connecting it is: pick the card, choose who it’s for, approve access at Productive. There’s nothing to type.
You’ll need: a Productive organization on the Ultimate plan with AI features enabled. Productive’s MCP server is only available there. A connection covers one Productive organization at a time.

​
What it gives the agent

Once connected and enabled on a project, the agent can search projects and tasks, read budgets, time entries, resourcing and sales deals, and answer questions in plain language (“who has capacity next month?”, “where is this project against budget?”). It can also make changes: create or update tasks, log time, update budgets, and create and change invoices and expenses. The card requests Productive’s two scopes, read and write, and nothing else.
Productive’s write access reaches billing data — time entries, budgets, invoices and expenses that your firm bills clients from. There is no approval step: a change runs as soon as the agent makes the call, under the connected Productive account (at User scope, the account of the member whose conversation made it). We recommend the User scope so that every change is attributable to a named person.

​
Choosing a scope

All three credential scopes are available — see Choosing who the credential belongs to for the full explanation of what each one means. For Productive specifically:
  • User (recommended) — each member connects their own Productive account. Productive respects that person’s role (finance versus delivery), and any change to time, budgets or invoices is made under, and attributable to, the member whose conversation made the call.
  • Project — each project connects its own Productive account. Rates, margins and budgets the agent reads are visible to every member of that project’s conversations.
  • Organization — one shared connection, typically a service account. Rates, margins and budgets the agent reads are visible to every project member it is enabled for, and changes are made under the shared account rather than a named person.

​
Connecting

1

Open the gallery

Go to Org settings → Integrations → Tools, select Add integration, and choose the Productive card.
2

Choose who it's for

Pick Organization, Project, or User. Only an Org Admin can register the integration at all; the scope decides who authenticates from here.
3

Approve access at Productive

For Organization scope, the Org Admin is sent to Productive to approve access, and returns to a Connected card. For Project scope, each project’s Project Admin does this from that project’s Tools tab. For User scope, each member does this from their own My Integrations page.
What happens next follows the same connect flow as any OAuth 2.0 integration — see Part 2 — Authentication for the general mechanics of discovery, the connected card, and what Reconnect required and Reconnect recommended mean. If you are in several Productive organizations, remember a connection covers one at a time.

​
Enabling it on a project

Connecting Productive at Organization or Project scope makes it available; a Project Admin still has to switch it on for each project from the Tools tab (see Part 3). For a Project-scoped connection, switching it on shows the project as not connected until that project’s own account is connected. For a User-scoped connection, the tool appears in the conversation as soon as the integration is enabled and any member has connected — a member who hasn’t connected yet gets a plain-language prompt to do so from My Integrations.

​
Reconnecting and access renewal

Parlé renews Productive’s access automatically in the background. If Productive stops accepting the stored authorization — revoked, expired, or the granted scopes changed — the card shows Reconnect required, and the integration stops working until whoever connected it approves access again.

​
Disconnecting and removing

Disconnecting a Productive connection, at any scope, deletes the stored credential from Parlé’s vault and removes the connection, so the agent can no longer use it. Before deleting it, Parlé asks Productive to revoke the access Productive issued. That request is best effort: if it fails, the disconnect still goes ahead. That Productive actually ends the access on its side hasn’t been confirmed against a live account, so to be certain it’s gone, also remove Parlé’s access yourself in Productive: check the authorized apps or AI connections in your Productive account settings and remove Parlé there. Removing the whole integration for your organization starts the same 14-day grace window as any other integration. See Part 5 — Maintaining an integration.