Samples

v1.0.0Coding Agentsstable

Agent samples built using the Strands Agents SDK.

agenticagentic-aiagentsaianthropic
Share:
761
Stars
0
Downloads
0
Weekly
0/5

What is Samples?

Samples is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to agent samples built using the strands agents sdk.

Agent samples built using the Strands Agents SDK.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Agent samples built using the Strands Agents SDK.

Use Cases

Agent samples with Strands Agents SDK
Multi-model bedrock agent examples
strands-agents

Maintainer

LicenseApache-2.0
Languagepython
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx samples

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Samples

The Strands Agents Samples repository provides a collection of reference implementations and demo agents built with the Strands Agents SDK, an AWS-developed framework for building AI agents in Python and TypeScript with a model-driven approach. The samples demonstrate patterns for multi-agent orchestration, RAG architectures, streaming responses, AWS Bedrock integration, and edge computing scenarios using just a few lines of code. Developers new to the Strands SDK use these samples as a starting point for understanding agent design patterns before building their own production agents.

Prerequisites

  • Python 3.10+ and pip installed (for Python samples), or Node.js 18+ and npm (for TypeScript samples)
  • AWS account with Bedrock model access enabled, or an alternative LLM provider API key
  • strands-agents and strands-agents-tools packages installed
  • An MCP client if integrating agent tools via MCP
1

Clone the samples repository

Clone the Strands Agents samples repository to explore the available agent examples.

git clone https://github.com/strands-agents/samples.git
cd samples
2

Create a virtual environment and install dependencies

Set up an isolated Python environment and install the Strands Agents SDK and its tools package.

python -m venv venv
source venv/bin/activate  # macOS/Linux
pip install strands-agents strands-agents-tools
3

Configure model provider credentials

Set up credentials for your chosen LLM provider. For AWS Bedrock, configure your AWS credentials. For other providers, set the relevant API key environment variable.

# For AWS Bedrock:
export AWS_ACCESS_KEY_ID=your_access_key
export AWS_SECRET_ACCESS_KEY=your_secret_key
export AWS_DEFAULT_REGION=us-east-1
4

Run a sample agent

Try the basic agent sample to confirm everything is working. The framework uses a model-driven approach where you describe what you want and the agent determines how to achieve it.

from strands import Agent

agent = Agent()
response = agent("Hello! Tell me a joke.")
print(response)
5

Configure as an MCP server

To expose a Strands agent as an MCP tool, add it to your MCP client configuration.

{
  "mcpServers": {
    "samples": {
      "command": "npx",
      "args": ["samples"]
    }
  }
}

Samples Examples

Client configuration

Basic MCP client configuration for a Strands Agents sample server.

{
  "mcpServers": {
    "strands-samples": {
      "command": "python",
      "args": ["-m", "strands_agent_server"],
      "env": {
        "AWS_DEFAULT_REGION": "us-east-1",
        "AWS_ACCESS_KEY_ID": "your_access_key",
        "AWS_SECRET_ACCESS_KEY": "your_secret_key"
      }
    }
  }
}

Prompts to try

Example prompts to explore Strands Agents capabilities.

- "Use the agent to summarize the latest AWS Bedrock announcements from the web"
- "Build a multi-agent pipeline where one agent retrieves data and another analyzes it"
- "Demonstrate a RAG agent that can answer questions about a local document collection"
- "Show me how to create a streaming agent that reports progress step by step"

Troubleshooting Samples

ImportError when importing from strands or strands_agents

Make sure you have installed both packages: 'pip install strands-agents strands-agents-tools'. If running inside a virtual environment, confirm the environment is activated before running the sample.

AWS Bedrock access denied or model not found

Ensure you have enabled the specific Bedrock model in your AWS account's Bedrock console under 'Model access'. Also verify your IAM user or role has the 'bedrock:InvokeModel' permission.

Samples produce unexpected output or don't run as described

The samples are for demonstration and educational purposes and may require modification for production use. Check the individual sample README files in each subdirectory for specific setup requirements and known limitations.

Frequently Asked Questions about Samples

What is Samples?

Samples is a Model Context Protocol (MCP) server that agent samples built using the strands agents sdk. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Samples?

Follow the installation instructions on the Samples GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Samples?

Samples works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Samples free to use?

Yes, Samples is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

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.

Quick Config Preview

{ "mcpServers": { "samples": { "command": "npx", "args": ["-y", "samples"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Samples?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides