Connectors and Claude Code - Claude Cheat Sheet

What a connector lets Claude read, change or do in your services, and keeping the blast radius small: scopes, per-chat access, and treating returned text as data. Then Claude Code: the approval loop, the billing gotcha, and safe first moves.

On the sheet:

- Where a connector plugs in: you, Claude, the connector, your service

- What a connector is: an MCP link to one of your services

- Add one, then switch it on: available to your account versus on in this chat

- What you authorize: OAuth, acting as you, scopes and revoking

- Keep your data safe: read-only, scoping, and per-chat access

- Text from a connector is data, not orders: guarding against prompt injection

- Review a write before it happens: see the tool, arguments and current values first

- What Claude Code is: Claude in your terminal, working on real files

- The approval loop: read, propose, approve, act, repeat

- The billing gotcha: a set API key that bills outside your plan

- Safe first moves in the terminal: start read-only, then one scoped change

Two A4 pages, printed front and back, sized to print once and keep beside you while you work. Written in short sentences and plain English, for readers whose first language is not English and clearer for everyone else because of it.

It pairs with the Connectors and Live Data and Claude Code at the Desk books, so you can learn each idea in full and then revise it here in two pages.

Every product fact on this sheet - every plan, price, limit, setting and menu - was checked against Anthropic's own published documentation before the file was made. This is an independent study guide, not affiliated with, authorized by, or endorsed by Anthropic. Instant PDF download. By M.R. Sterling.