Skip to main content

Tools

A kill switch for every AI, and an expiry date

Turn an AI off and its next call is refused. Every AI's access also has an end date.

Brad's MacBook On 4m ago
Claude Code On 22m ago
Cursor Not set up Never
Studio Mac Mini Off 6d ago

What it does

One switch turns an AI off, everywhere at once

Flip it and the next call from that AI is refused on every connected account. Flip it back and it resumes. The log shows what was refused in between.

Revoke is final; the history stays

Revoke ends the access for good. What that AI did is still on the record, because the record outlives the AI.

Every AI's access has an end date

You pick the date when connecting. Extending is one click: a day, a week, 30 days or a year. Two weeks unused and the access revokes itself.

Expires

Everything plugged into Claude Code stops working then, so nothing stays signed in forever. Give it more time whenever you like.

Stops working in 21 days on

More in Tools

The same tools in every AI that speaks MCP

One address, pasted once into ChatGPT, Claude, Claude Code or Cursor. Each gets the same accounts and rules.

See how it works

Gmail and Calendar from the command line, for people and coding agents

Gmail, Calendar and web search from a terminal. Claude Code and Codex run the same commands.

See how it works

Passwords and API keys never reach the AI

Connected accounts are held by gbrain. An AI gets the result of a call, never the key.

See how it works

A permission level for every application an AI can reach

Gmail has four levels, Calendar two, web search is on or off. Set per application; every AI follows.

See how it works

A log of every call an AI makes with connected accounts

One row per call. Who asked, which AI, which account, what it did, whether it was allowed.

See how it works

Spin up a gbrain

A workspace of your own in about a minute, with this in it.