Get the FREE Ultimate OpenClaw Setup Guide →

samples

Agent samples built using the Strands Agents SDK.

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio strands-agents-samples node \
  --env PLACEHOLDER="No MCP server command defined for this repository. Configure as needed."

How to use

The Strands Agents Samples repository provides demonstrative Python and TypeScript examples that showcase how to build and run AI agents using the Strands Agents SDKs. The Python side uses the strands-agents package to instantiate an Agent and issue prompts, while the TypeScript side demonstrates creating an Agent with the strands-agents-sdk and invoking it to obtain responses. These samples are intended for learning, experimentation, and as a reference for integrating the SDKs into your own applications. To get started, explore the Python and TypeScript tutorials and adapt the patterns to your use cases, such as multi-agent coordination, retrieval-augmented generation, or simple conversational assistants.

How to install

Prerequisites:

  • Python 3.10 or higher with pip
  • Node.js 18 or higher with npm or yarn

Python setup (per Python samples):

  1. Create and activate a virtual environment:
python -m venv venv
# On macOS/Linux:
source venv/bin/activate
# On Windows:
venv\Scripts\activate
  1. Install the Python packages used in the samples:
pip install strands-agents strands-agents-tools
  1. Run or try the Python snippet from the tutorials (e.g., creating an Agent and sending a message).

TypeScript setup (per TypeScript samples):

  1. Ensure Node.js is installed (v18+).
  2. Install the SDK package:
npm install @strands-agents/sdk
  1. Run the TypeScript example or tutorial files using ts-node or build with your preferred workflow.

General tips:

  • Review the tutorials under 01-tutorials for Python and the TypeScript tutorials for starter examples.
  • Configure any required model providers or API keys as indicated by the tutorials or the referenced documentation links in the repository.

Additional notes

Tips and common issues:

  • Ensure Python and Node environments are isolated (virtualenv for Python, project-local node_modules).
  • For Python, verify pip is available and network access is unrestricted when installing dependencies.
  • Some samples may require additional configuration for model providers or API access; follow the Model Provider Setup guidance linked in the repository.
  • When running tutorials, environment variables for API keys or endpoints may be necessary; use a .env file or export variables as appropriate.
  • This repository focuses on educational demos and is not intended for production use without applying security and robustness enhancements.

Related MCP Servers

Sponsor this space

Reach thousands of developers