Your agents don’t need to persist. Your purpose does.
How do I connect Google Calendar to ChatGPT?
This archived article remains available at its original address. Unl, your why agent, carries the decisions you settle and why into your AI work. See how it works.
Events with filters, search, free/busy across accounts — the calendar read serves ChatGPT the week as booked, not as hoped.
Direct answer: connect Google Calendar over MCP to ChatGPT. In ChatGPT, add it from the connector settings (developer mode); the tool's own docs carry the current path. Authorised, ChatGPT reads calendars and events (filterable), runs event search, and checks free/busy across every account you authorise — scheduling questions answered from the diary itself.
The diary, interrogated
Tomorrow's real shape, the week's meeting total, the slot that clears both calendars — read rather than reconstructed. Free/busy across accounts quietly solves the two-diary life.
Meeting load is a budget
Worked case: you ratified a meeting-load cap — fifteen meeting-hours a week, hard, because a month at twenty-two once produced zero deep work and a strong opinion about whose fault that was. The calendar hosts twenty-two as happily as fifteen; the cap is your budget over it.
Through Unl the week's read arrives budgeted: seventeen meeting-hours booked — two over your cap, the zero-deep-work month attached. Accepting the next invite becomes a decision with a visible cost instead of a reflex.
Calendar to ChatGPT reads the week as booked; through Unl the week answers to the load budget you ratified — hour eighteen gets refused by your own arithmetic.
Reads through Unl arrive with measured context — in the presence of the decisions you’ve already settled. It works today: 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 the Calendar read include?
Calendars, events with filters, search, and free/busy across accounts — the observational scheduling surface, client-agnostic.
Why a cap instead of blocking focus time?
Blocks defend hours; a ratified cap governs totals. They compose — the cap catches the week where every individual booking looked reasonable.
Does the rule follow me between assistants?
Yes — it lives in Unl, not in the client. Fifteen hours is fifteen hours whichever assistant reads the week.
What if you take the nineteenth hour anyway?
Then you take it, and nothing here objects. The budget is yours and so is the override. What changes is that the week goes on record as one you chose to overrun, so when the same month repeats you are reading a pattern rather than remembering a busy week.
What this is
Your agents don’t need to persist. Your purpose does.
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 works inside Claude, Claude Code, ChatGPT and Cursor, and connects 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 to start. Paid plans from $10 a month.