Claude Agent SDK (TypeScript) FAQs

Question 1

Can I use this SDK with non-Anthropic models like GPT-4 or Gemini?

Accepted Answer

No, the Claude Agent SDK is specifically optimized for and locked to Anthropic's Claude models. It supports Claude via the direct Anthropic API, Amazon Bedrock, Google Vertex AI, or Azure AI Foundry.

Question 2

Does it support Model Context Protocol (MCP)?

Accepted Answer

Yes, the SDK allows you to connect to external MCP servers via stdio, SSE, or HTTP, and also lets you create in-process MCP tools using Zod schemas for structured data validation.

Question 3

What is the Claude Agent SDK?

Accepted Answer

It is a TypeScript library that allows you to run Claude's agentic loop programmatically. It provides access to the same tools as the Claude Code CLI—like Read, Write, and Bash—but through a structured API.

Question 4

How do I handle session persistence with the SDK?

Accepted Answer

You can capture the session_id from the initial system message and pass it as a 'resume' option in subsequent queries to maintain context across different execution blocks.

Question 5

How do permissions work in the SDK?

Accepted Answer

You can use built-in modes like 'acceptEdits' or 'plan', or implement a custom 'canUseTool' callback to approve or deny specific tool executions based on the command or file path.

Claude Agent SDK (TypeScript)

Key Features

Use Cases

Claude Agent SDK (TypeScript)

Key Features

Use Cases