Skip to main content
gbrain
Menu
Get Started

Claude Code

Claude Code, with your accounts in the room.

Your mail, calendar and web search mid-task, no key in mcp.json.

Claude Code is good at the code in front of it. It cannot read the email thread where a bug was reported or check when the fix is due, so you end up pasting that context in yourself.

gbrain connects on two sides. Over MCP it gives Claude Code tools: mail search, calendar, web search, page fetching. And your gbrain workspaces run Anthropic models, so the company behind your assistant is also behind what your workspaces think with.

You choose which tools it gets, and the token in mcp.json can be revoked at any time. No API keys on disk.

One endpoint connects Claude Code

Not one per service. What this client can call is decided by its permission, not by the address, and the token comes from the client's own page in the workspace, minted once and shown once. 

claude mcp add gbrain https://gbrain.io/mcp --header "Authorization: Bearer <token>"

Every application Claude Code gets

Connect one in the browser and it answers here, under the same permission and the same record as everywhere else.

Your workspaces run Anthropic models too

The company behind Claude Code also makes models your workspaces can think with. Each one has its own page, and Models lists the full set.

The other places a connection answers are on Works with, and Tools explains the permission, the ceiling and the record they share.