Prospecting
Apify
Run any of Apify's hosted scrapers, Google Maps, LinkedIn, Amazon and more, and read their output from Claude or ChatGPT through Tulina's MCP server.
Official site: apify.com
What it does
- Run pre-built scrapers from the Apify Store and read their output
The value here is breadth, not depth — thousands of pre-built scrapers already maintained against whatever site they target, rather than building and maintaining one yourself. It's read-only against each scraper's own output shape, and two different scrapers for the same kind of site can return different fields, so what comes back depends on which one ran.
What is an Apify MCP server?
Tulina's own MCP server, the same one every connector in this catalogue runs through. Pick a pre-built scraper from the Apify Store and run it, a Google Maps census, a LinkedIn search, an Amazon listing pull, and read its output in Claude or ChatGPT without opening Apify's console or matching each scraper's own field shape by hand.
Why through Tulina
Most systems now publish their own way for a model to reach them, and that is a good thing — it is what Tulina connects to. The connection was never the hard part. Deciding who may use it, what it is allowed to return, and what the model knows before it asks: that is.
The keys stay in one place
Connect Apify 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 is handed more access than they need. Revoke it once and everything running on it stops.
What leaves is filtered before it leaves
Roles decide who can reach Apify at all. Beyond that, a policy on the connector itself decides what comes back: fields dropped, identifiers masked or hashed, people pseudonymised. The data is minimised at the source rather than after it has already reached a model.
Every call is on the record
Runs are logged for the organisation — what was called, by whom, when. That is what makes an automated action reviewable after the fact, and what a security review asks for first.
The run starts knowing your company
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 Apify returns something usable instead of something generic.
Processes that run on Apify
Brief every cold call before it starts
Every account on the call list gets a note before anyone dials, carrying the signals found on it, what the lead has said publicly, and one opener grounded in both.
Build a target list from a sentence
Describe the companies you want in one sentence, and get them sourced, scored on dated signals, enriched, deduplicated against your CRM, and staged as a campaign.
Find buyers engaging with competitors
Everyone who engages with a competitor's posts gets found, scored against your ICP, enriched, and staged for outreach with a human approving the list.
Revive deals that went cold
Deals lost more than 90 days ago come back with fresh signals, contacts checked for job moves, and the features they asked for that have since shipped.