Directory / Claude Agent SDK

Claude Agent SDK

Agent framework · Anthropic · Last checked 2026-10-16

Shares Claude Code's permission system. canUseTool handles approvals for calls not already allowed, and PreToolUse hooks run on every call.

Overall: A (2.50 avg over 6 verified criteria)

Lock this down first

Put must-hold checks in a PreToolUse hook, not in canUseTool, which skips pre-approved calls.

Criterion	Rating	Notes
Permission granularity	3/3
Human approval gates	3/3
Sandboxing	2/3	Same Bash sandbox as Claude Code, set programmatically.
Secrets handling	Unverified	Not confirmed in the docs we checked.
Audit logs	2/3	OpenTelemetry metrics and events, opt-in.
Kill switch / interrupt	3/3	AbortController cancels a query; interrupt() in streaming mode.
Network egress control	2/3	Sandbox network allowlist, including strict mode.

Unverified: Secrets handling. That means we could not confirm it in public docs, not that it is missing.