Think inside your AI world.
How do I connect Close to Claude?
Close is built around calling and follow-up discipline, which makes it a natural fit for reads that answer 'who is slipping through?'
Direct answer: add Close's MCP server in Claude — Settings → Connectors, authorise the account; in Claude Code, 'claude mcp add'. Claude then reads your CRM live: leads, opportunities, calls, emails and the follow-up state that Close is organised around.
Follow-up questions, answered from the record
Which leads had a first call but no second touch, what yesterday's call notes actually said, where each opportunity stands this week — read from the account in conversation, which suits a tool whose users live in outreach rhythm.
The cadence you promised yourselves
Say the team ratified a follow-up cadence — every qualified lead gets a touch within five working days, since a pipeline audit once found a third of losses were simply silence. Close logs every touch and its timestamp; the five-day promise is a standard about the logs, kept nowhere in them.
The book of leads, measured
Through Unl the lead read arrives held to the cadence: six qualified leads past five days untouched — the silence pattern you audited, recurring. The Monday pipeline meeting opens on breaches of your own standard instead of a scroll through lists.
Close in Claude reads the outreach record; through Unl it reads that record against the cadence you ratified — silence gets named before it becomes a lost quarter.
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 Claude read from Close?
Leads, opportunities, calls, emails and follow-up state — the live working record of an outreach-driven sales motion.
Same connection for ChatGPT?
Yes — MCP is client-neutral; Close's server connects to ChatGPT and other MCP clients identically.
What cadence rules work best ratified?
The ones with evidence: touch windows priced by an audit, qualification bars priced by bad-fit deals. A rule that carries its receipts gets respected — by the team and by every read.
What if silence was the right call for that account?
Then say so, and the silence stops being ambiguous. The cadence rule surfaces the gap; it does not judge it. What it prevents is the case where nobody can tell whether an account went quiet on purpose or was simply dropped.
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.