CRMConnector
Folk
Read, search and update Folk contacts, companies and pipeline stages, and add notes, from Claude or ChatGPT, through Tulina's own MCP server.
Official site: folk.app
What it can do
1 read/2 write
- 01Read
Read and search contacts, companies and groups
- 02Write
Create and update records, and move deals across pipeline stages
- 03Write
Add notes tied to a contact or company
Built around groups rather than one fixed pipeline shape — contacts and companies belong to groups, and each group carries its own custom fields. Useful for a workflow that needs to read or write both structured records and the unstructured notes tied to them, not just one or the other.
How do you connect Folk to Claude and ChatGPT?
Through Tulina's own MCP server, not Folk's. Read and search contacts, companies and groups, create or update a record, or move a deal across pipeline stages, in the same chat as the outreach it feeds, whether that chat is Claude or ChatGPT.
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 Folk 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 Folk 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 Folk returns something usable instead of something generic.
Processes that run on Folk
Find contacts for signal accounts
Companies that already showed interest but have nobody linked get the right people found by role, deduped, and added to outreach automatically.
6 steps →Keep your knowledge base current
An AI knowledge base kept current each morning: yesterday's activity in your tools is read, stale pages are rewritten in place, and a missed day sends an alert.
7 steps →Pull insights from call recordings
Conversation intelligence from a name, company or email: the right sales call found in your CRM or recordings, returned with a summary, the link saved back.
5 steps →Re-engage quiet accounts
Quiet paying accounts get one relevant note each, grounded in what they said last, with the outreach date stamped back so nobody's emailed twice.
7 steps →Turn website visitors into outreach
Website visitor tracking that ends in outreach: each company is checked against your CRM, and the few with real intent get a named contact and a drafted note.
7 steps →
