Skip to content
← Connectors

ProspectingConnector

Unipile

One Unipile subscription, held in Tulina's MCP server, so each person links LinkedIn, WhatsApp, Telegram, Instagram, Messenger or X in Claude or ChatGPT.

Official site: www.unipile.com

What it can do

3 read

  • 01
    Read

    Hold the subscription once for the organization, in the vault

  • 02
    Read

    Let each person link their own LinkedIn, WhatsApp, Telegram, Instagram, Messenger or X account

  • 03
    Read

    Run each session on a real hosted browser rather than a pasted cookie

This is the account, not a channel. The organization puts the Unipile subscription in place once — its own key, or the platform's with hosted messaging granted by an admin — and each of the six networks is then its own connection that a person links separately. LinkedIn does not bring WhatsApp with it, and turning one on leaves the others off.

That granularity is the point. Sessions run on a real browser with a residential proxy, and each acts as the person who opened it rather than as a shared bot, so the scope of what a model can send is decided per network and per person. Reach here scales fast, which makes that the thing worth deciding upfront rather than after the first run.

How do you connect Unipile to Claude and ChatGPT?

Through Tulina's own MCP server, not a separate one. Community projects already wrap Unipile's raw API as their own MCP servers, and Unipile ships a native MCP server of its own for email; this card is neither — it is the subscription that Tulina's LinkedIn, WhatsApp, Telegram, Instagram, Messenger and X connectors sit on. Put it in place once, in the vault, then each person links their own account per network from the same chat where Claude or ChatGPT is already working, on a hosted browser rather than a cookie pasted into a script.

Why through Tulina

The connection was never the hard part.

Most systems now publish their own way for a model to reach them, and that is good: it is what Tulina connects to. The hard part is deciding who may use it, what it is allowed to return, and what the model knows before it asks.

  • The keys stay in one place

    YouTeamOrganisation

    Connect Unipile once. The credential is encrypted in a vault, never held in clear, and never pasted into a chat or a workflow file. A person uses their own key where they have one, their team's where they do not, the organisation's after that, so nobody is blocked and nobody holds more access than they need. Revoke it once and everything running on it stops.

  • What leaves is filtered before it leaves

    fields droppedmasked or hashedpseudonymised

    Roles decide who can reach Unipile at all. Beyond that, a policy on the connector itself decides what comes back. The data is minimised at the source rather than after it has already reached a model.

  • Every call is on the record

    whatwhowhen

    Runs are logged for the organisation. That is what makes an automated action reviewable after the fact, and it is what a security review asks for first.

  • The run starts knowing your company

    namingkey accountsdecisions

    A direct connection gives a model access. It does not tell it how your company names things, which accounts matter, or what was decided last quarter. Tulina carries that across every tool, so the same request against Unipile returns something usable instead of something generic.

Processes that run on Unipile

None published yet.

See Tulina in a 30-minute demo.

Book a demo