Your agents don’t need to persist. Your purpose does.

How do I connect Google Drive to ChatGPT?

Drive over MCP ends the download-and-attach loop for ChatGPT too — files searched and read where they live.

Direct answer: connect Google Drive 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 searches and reads your Drive in place — the contract, the deck, the folder of versions — no shuttle between storage and conversation.

Documents answered in place

The signed agreement's actual clause, the latest deck's pricing slide, the folder's newest version — read directly. Document questions collapse to one step.

Files outlive their welcome

Worked case: you set a retention rule — client project files move to archive ninety days after project close, after a due-diligence scramble once surfaced working files from four dead projects in the live folder tree. Drive keeps everything indefinitely by temperament; that live means live is filing law you imposed.

Through Unl the folder read arrives with the law applied: files from two closed projects past ninety days still live — against your rule, the due-diligence scramble attached. The archive happens on schedule because the schedule reads along.

Drive to ChatGPT reads files where they live; through Unl the file tree answers to the retention law you set — dead projects leave the live folders on your schedule.

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 Drive connection allow?

Search and read over authorised files, in place — the same surface every MCP client gets.

Does Unl copy any file contents?

No — it measures reads against your rules and stores your decisions only. Files stay in Drive; rules live in Unl.

What filing rules decide well?

Retention windows, current-template rules, a 'signed versions live here' law. Filing rules are cheap to honour and expensive to lack — ideal decision material.

What if an archived project comes back?

Then you bring it back, and the archiving cost you nothing but a move. Retention rules fail in the other direction: folders nobody dares touch in case someone needs something. Deciding the schedule in advance is what makes the move reversible instead of contentious.

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. 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·You decide·Model agnostic·Your data

The right information

Connect Unl to bring the right information into the moment.

Your sources, read against the criteria you set.

Add Unl to your AI

The full product, open. Free to start. Paid plans from $10 a month.