Think inside your AI world.
How do I connect Google Drive to Claude?
Drive over MCP means Claude reads the file where it lives — no download, upload, re-upload cycle — which quietly fixes the most annoying loop in AI-assisted document work.
Direct answer: connect Google Drive over MCP in Claude — Settings → Connectors, authorise ('claude mcp add' in Claude Code). Claude then searches and reads your Drive files in place: the proposal, the contract, the deck, the folder of last year's versions. The copy-paste shuttle between Drive and the conversation ends.
Files read where they live
Find the latest master services agreement, read the pricing appendix, compare this proposal against the one that won in March — done against the files themselves. Search plus read-in-place covers most of what document questions actually need.
The staleness problem boilerplate breeds
Worked case: you ratified a current-terms rule — proposals go out on this quarter's rate card and the revised liability clause, after a recycled document once quoted rates two rises old. Drive keeps every version faithfully, which is exactly the problem: the stale one reads as confidently as the current one.
Documents, read against what currently stands
Through Unl the proposal read arrives checked: this draft carries the old rate card — your current-terms ruling flags it, with the two-rises story attached. Version archaeology becomes rule enforcement. Drive holds the documents; Unl holds which of their contents you still stand behind.
Drive to Claude reads your files in place; Drive through Unl reads them against what currently stands — stale boilerplate gets caught by the ruling, not by luck.
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 the Drive MCP connection do?
Search and read over your Drive files, scoped to your authorisation — documents readable in conversation without the download-upload shuttle.
Does it connect to ChatGPT too?
Yes — standard MCP surface, connectable from any capable client through its own settings menu.
How do document rules work in practice?
You ratify what 'current' means — the live rate card, the standing clause set, the approved template — with the incident that made it matter. Any document read that touches those areas arrives with the ruling applied.
What if nobody knows which version of the document is current?
The ruling is what is current, and the document is evidence of it. That inversion is the whole point — if the only record of a decision is a file somebody may have superseded with a copy called 'final v3', then this does not help you, and the first job is getting the decision out of the file.
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.