Think inside your AI world.
How do I connect Close to ChatGPT?
Close's calling-centred CRM reads into ChatGPT over MCP — leads, calls, emails, the rhythm of outreach as data.
Direct answer: connect Close's MCP server to ChatGPT. In ChatGPT, add it from the connector settings (developer mode); the tool's own docs carry the current path. Authorised, ChatGPT reads leads, opportunities, calls and emails live — the working record of an outreach motion, available to the assistant you already think in.
Outreach state, retrieved
Yesterday's call notes, the leads awaiting a second touch, this week's opportunity movement — read from the account. Outreach teams live and die on rhythm; retrieval makes the rhythm inspectable.
No call ends without a next step
Worked case: you ratified a next-step rule — no call gets logged as complete without a concrete next step and a date, because a pipeline post-mortem found 'great call!' notes leading precisely nowhere. Close stores whatever the rep types; that a note without a next step is an unfinished call is your standard of finished.
Through Unl the call-log read arrives held to it: three completed calls this week with no next step recorded — unfinished by your rule, the nowhere-notes lesson attached. Coaching moments surface from the record itself.
Close to ChatGPT reads the outreach record; through Unl the record answers to the completeness standards you ratified — a call without a next step gets flagged as the unfinished thing it is.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. The reach lane is live: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.
Read further
Questions people ask
What does ChatGPT read from Close?
Leads, opportunities, calls and emails — the live outreach record, same surface as every MCP client.
Does this change how reps work in Close?
No — Close stays the workflow. The measured layer changes what reviews see: the record read against the standards you set for it.
What outreach standards ratify well?
Next-step completeness, touch windows, qualification bars — standards a post-mortem has already priced. They arrive at read time with the post-mortem attached.
What if the honest next step is none?
Then say so, and record it as a close rather than leaving the field empty. An empty field and a deliberate ending look identical to any rule, and only one of them is finished work. The discipline is naming the ending, not inventing an action to fill the gap.
What this is
Think inside your AI world — you stay in command
Save the thoughts, decisions and targets worth keeping, each with its reasoning, carried into every AI session the moment they matter. A new unit of exchange between you and your AI: the Settled Why with standing that travels. Unprompted.
Your whole AI world. What you decided at the epicentre. It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector — quick to connect, in a couple of steps.
MCP native·Human settled·Model agnostic·Your data
Measured Context
Connect Unl to bring the right information into the moment.
Your sources, read against the criteria you set.
The full product, open. Free at launch.