What is Aws Strands Agents Mcp Demo

The AWS Strands Agents MCP server is a platform that integrates third-party APIs, such as Shutterstock and the National Weather Service (NWS), to enable AI agents to perform contextual searches based on current environmental conditions. It utilizes the Model Context Protocol (MCP) to standardize interactions between agents and external services.

Use cases

This MCP server can be utilized in various applications, including dynamic content delivery based on real-time weather conditions, personalized media searches tailored to users’ local environments, and enhancing creative projects by automatically sourcing relevant imagery and media assets from Shutterstock based on contextual data.

How to use

Users can set up the MCP server by cloning the provided GitHub repository and installing necessary packages. After configuring environment variables such as the Shutterstock API Token, users can start the MCP servers for STDIO and HTTP transports. Subsequently, they can run Strands Agents that leverage the MCP server to facilitate searches and retrieval of context-sensitive media from Shutterstock.

Key features

Key features of the MCP server include seamless integration with third-party APIs, the ability to run multiple agents concurrently, context-aware media retrieval based on dynamic conditions, and the use of standardized protocols to streamline interactions between AI agents and external services.

Where to use

This MCP server can be effectively deployed in web applications, mobile apps, and creative software tools that require on-demand access to stock photography and media based on situational context. It can also be integrated into marketing platforms and content creation services that aim to automate content sourcing and enhance user engagement.

AWS Strands Agents: Building and Connecting Your First Model Context Protocol (MCP) Server

Overview

Deploy an MCP server that searches for stock photography based on your current location and conditions using third-party APIs, and orchestrate it with Strands Agents and the Amazon Q Developer CLI.

The Model Context Protocol (MCP) provides a standardized interface that enables AI agents to interact seamlessly with external services. In this post, we’ll demonstrate how to build an MCP server that integrates with Shutterstock — my favorite platform for high-quality licensed images, videos, music, and creative tools — using their robust API. We’ll then show how to expose these rich media search capabilities to agents developed with Strands Agents, AWS’s code-first framework for building production-ready AI agents. By orchestrating multiple agents, we’ll enable them to access the National Weather Service (NWS) API, intelligently select contextually relevant photos based on current weather conditions, and deliver results that showcase the power of reasoning and context-aware automation.

JavaScript/Node.js MCP Servers based on: https://github.com/lucianoayres/mcp-server-node.

Prerequisites

• Git distributed version control system
• Node.js v22.16.01 LTS or newer (MCP servers)
• npm, Yarn, or other Node.js package manager
• Python 3.13.x (Strands Agents)
• pip, Poetry, or another Python package manager
• AWS Account (for access to Amazon Bedrock generative AI models; other model providers are also supported)
• Free Shutterstock Test Account and Token (Register at Shutterstock Developers)
• Optional: Amazon Q Developer CLI for last section of post

Installation

1. Clone Repository and Install Packages

npm install -g corepack # if using yarn

git clone https://github.com/garystafford/aws-strands-agents-mcp-demo.git
cd aws-strands-agents-mcp-demo

yarn install

2. Start MCP Servers

# terminal window 1: STDIO transport
# environment variables are set by MCP server with STDIO
export API_KEY=abc-1234567890
export SHUTTERSTOCK_API_TOKEN=<YOUR_SHUTTERSTOCK_API_TOKEN>
node mcp-server.js

# terminal window 2: Streamable HTTP transport
# environmental variables are set by agent with Streamable HTTP
node mcp-server-remote.js

3. Install Strands Agents

python -m pip install virtualenv -Uqqq
python -m venv .venv
source .venv/bin/activate

python -m pip install pip -Uqqq
python -m pip install -r requirements.txt -Uqqq

4. Start Strands Agents

export API_KEY=abc-1234567890
export SHUTTERSTOCK_API_TOKEN=<YOUR_SHUTTERSTOCK_API_TOKEN>

python agent_stdio_multi_agent.py

The contents of this repository represent my viewpoints and not of my past or current employers, including Amazon Web Services (AWS). All third-party libraries, modules, plugins, and SDKs are the property of their respective owners.