ProspectingConnector
AI Ark
Search people and companies by LinkedIn profile signal through Tulina's dedicated AI Ark line, from Claude or ChatGPT, apart from the shared LinkedIn access.
Official site: ai-ark.com
What it can do
1 read
- 01Read
Search people and companies by LinkedIn profile signal
A dedicated search path, distinct from the shared LinkedIn connector's own baked-in access — that one runs on Tulina's platform-wide AI Ark capacity, free to use and nothing to configure. This connector is a separate, keyed connection instead: its own credential, its own scope, useful when the shared access is rate-limited or a workflow needs a dedicated line it can revoke on its own.
Does AI Ark have an MCP server?
Yes, and it is reached here through Tulina's own MCP server rather than AI Ark's directly, so the same connection that carries every other tool also carries this one, in Claude and ChatGPT alike. It runs the same person-and-company search across LinkedIn's graph as the shared access built into the platform, but on its own keyed credential, useful when the shared line is rate-limited or a workflow needs a connection it can revoke by itself.
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 AI Ark 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 AI Ark 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 AI Ark returns something usable instead of something generic.
