By Vero SecurityBuilt and funded by Vero Security, the AI Security Engineering platform.Read the charter

Claude Agent SDK

The Claude Agent SDK exposes the agent harness behind Claude Code as a Python and TypeScript library. It inherits Claude Code's permission rules, permission modes, hooks, and MCP support. You can enforce controls in code before any tool runs and pair them with an OS-level sandbox.

Read in this order

  1. OfficialAgent SDK overviewStart here: what the SDK gives you and how the agent loop runs.
  2. OfficialConfigure permissions (Agent SDK)How to gate each tool call with rules and modes in code.
  3. OfficialIntercept and control agent behavior with hooks (Agent SDK)How to intercept tool calls to log, block or modify them.

Save your progress

We email you a sign-in link. No password.

By signing in you agree to the terms. The privacy policy explains how we use your details.

Join the AI security engineering community

Free. Roadmap updates, chapters near you, and first word when credentials open.

We’ll email you community updates. Unsubscribe anytime. By sending this you agree to the terms. The privacy policy explains how we use your details.