AWS Genai SDK TypeScript
A model-driven approach to building AI agents in just a few lines of code.
What is AWS Genai SDK TypeScript?
AWS Genai SDK TypeScript is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to model-driven approach to building ai agents in just a few lines of code.
A model-driven approach to building AI agents in just a few lines of code.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A model-driven approach to building AI agents in just a few
Use Cases
Maintainer
Works with
Installation
NPM
npx -y @strands-agents/sdkManual Installation
npx -y @strands-agents/sdkConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use AWS Genai SDK TypeScript
The Strands Agents TypeScript SDK is a model-driven framework for building AI agents in just a few lines of code, primarily targeting Amazon Bedrock and OpenAI as LLM backends. It provides an Agent class that manages the full interaction loop between users, models, and tools — including built-in tools for file editing, HTTP requests, and note-taking — plus first-class MCP client support so agents can consume any MCP server as a tool source. Developers use it to build autonomous agents, multi-agent graphs and swarms, and structured-output pipelines on AWS infrastructure.
Prerequisites
- Node.js 20 or higher
- npm or yarn package manager
- AWS credentials configured (for Bedrock): AWS_ACCESS_KEY_ID, AWS_SECRET_ACCESS_KEY, AWS_DEFAULT_REGION, with Claude Sonnet 4 model access enabled
- OPENAI_API_KEY if using the OpenAI provider instead of Bedrock
- An MCP client such as Claude Desktop if embedding MCP server functionality
Install the SDK
Install the @strands-agents/sdk package from npm into your TypeScript or JavaScript project.
npm install @strands-agents/sdkConfigure AWS or OpenAI credentials
For Amazon Bedrock (the default provider), ensure your AWS credentials are set in the environment and that you have enabled access to the Claude Sonnet 4 model in your AWS region. For OpenAI, set the OPENAI_API_KEY environment variable.
# For Bedrock
export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
export AWS_DEFAULT_REGION=us-east-1
# For OpenAI
export OPENAI_API_KEY=sk-...Create a basic agent
Import the Agent class and invoke it with a natural language prompt. By default it uses the Bedrock provider with Claude Sonnet 4.
import { Agent } from '@strands-agents/sdk';
const agent = new Agent();
const result = await agent.invoke('What is the square root of 1764?');
console.log(result);Add MCP server tools
Pass an MCP client directly as a tool source in the Agent constructor. The agent will automatically discover and invoke the tools exposed by the connected MCP server.
import { Agent, McpClient } from '@strands-agents/sdk';
const client = new McpClient({ transport: myTransport });
const agent = new Agent({ tools: [client] });
const result = await agent.invoke('Search for recent news about AI agents');Configure in Claude Desktop
To use the Strands TypeScript SDK as an MCP server within Claude Desktop, add the npx launcher to your config file.
{
"mcpServers": {
"strands-sdk": {
"command": "npx",
"args": ["-y", "@strands-agents/sdk"],
"env": {
"AWS_ACCESS_KEY_ID": "AKIA...",
"AWS_SECRET_ACCESS_KEY": "...",
"AWS_DEFAULT_REGION": "us-east-1"
}
}
}
}AWS Genai SDK TypeScript Examples
Client configuration
Claude Desktop configuration for the Strands Agents TypeScript SDK using Amazon Bedrock credentials.
{
"mcpServers": {
"strands-agents-sdk": {
"command": "npx",
"args": ["-y", "@strands-agents/sdk"],
"env": {
"AWS_ACCESS_KEY_ID": "YOUR_AWS_ACCESS_KEY",
"AWS_SECRET_ACCESS_KEY": "YOUR_AWS_SECRET_KEY",
"AWS_DEFAULT_REGION": "us-east-1"
}
}
}
}Prompts to try
Prompts that exercise the agent's built-in tools and multi-agent capabilities.
- "Read the file ./src/index.ts and explain what it does"
- "Make an HTTP GET request to https://httpbin.org/json and summarize the response"
- "Create a multi-agent workflow where one agent researches a topic and another writes a summary"
- "Use structured output to extract name, email, and role from this text: [paste text]"Troubleshooting AWS Genai SDK TypeScript
Bedrock model invocation fails with AccessDeniedException
Ensure your AWS IAM user or role has permission to invoke the Bedrock model you selected and that model access has been explicitly enabled in the AWS Bedrock console for your region.
MCP client tools are not available to the agent
Pass the McpClient instance in the tools array when constructing the Agent, not after construction. Verify the MCP transport is connected and the server is running before creating the agent.
TypeScript compilation errors referencing missing types
Ensure your tsconfig.json targets ES2022 or later with moduleResolution set to node16 or bundler. Run npm install to confirm all peer dependencies including zod are installed.
Frequently Asked Questions about AWS Genai SDK TypeScript
What is AWS Genai SDK TypeScript?
AWS Genai SDK TypeScript is a Model Context Protocol (MCP) server that model-driven approach to building ai agents in just a few lines of code. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install AWS Genai SDK TypeScript?
Install via npm with the command: npx -y @strands-agents/sdk. Then add the server configuration to your AI client's JSON config file (e.g., claude_desktop_config.json or .cursor/mcp.json).
Which AI clients work with AWS Genai SDK TypeScript?
AWS Genai SDK TypeScript works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is AWS Genai SDK TypeScript free to use?
Yes, AWS Genai SDK TypeScript is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
AWS Genai SDK TypeScript Alternatives — Similar Coding Agents Servers
Looking for alternatives to AWS Genai SDK TypeScript? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up AWS Genai SDK TypeScript in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use AWS Genai SDK TypeScript?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.