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

Model Context Protocol (MCP) Server and AWS Strands Agents Demonstration

Local serverstdioPython

What is the AWS Strands Agents: Building And Connecting Your First Model Context Protocol (MCP) Server MCP server?

Model Context Protocol (MCP) Server and AWS Strands Agents Demonstration. Exposed over MCP by the aws strands agents: building and connecting your first model context protocol (mcp) server mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

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)

Its toolset

Everything the assistant can do here goes through one of these:

  • Optional — Amazon Q Developer CLI for last section of post

Configuration

You will need 3 environment variables: API_KEY, SHUTTERSTOCK_API_TOKEN, YOUR_SHUTTERSTOCK_API_TOKEN. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

  • 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

Adding it to your client

The server ships on npm as corepack, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

When to reach for it

This sits in the cloud and infrastructure group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. AWS Strands Agents: Building And Connecting Your First Model Context Protocol (MCP) Server's toolset — Optional — is a fair guide to whether it matches your workflow. It is maintained by garystafford; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the aws strands agents: building and connecting your first model context protocol (mcp) server mcp server does with a few real requests.

Available tools

ToolWhat it does
OptionalAmazon Q Developer CLI for last section of post

How to install the AWS Strands Agents: Building And Connecting Your First Model Context Protocol (MCP) Server MCP server

{
  "mcpServers": {
    "aws-strands-agents-mcp-demo": {
      "command": "npx",
      "args": ["-y", "corepack"],
      "env": {
        "API_KEY": "your-value",
        "SHUTTERSTOCK_API_TOKEN": "your-value",
        "YOUR_SHUTTERSTOCK_API_TOKEN": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

  • 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
VariableDescriptionRequired
API_KEYCredential the server authenticates with.Yes
SHUTTERSTOCK_API_TOKENCredential the server authenticates with.Yes
YOUR_SHUTTERSTOCK_API_TOKENCredential the server authenticates with.Yes

Example prompts to try

  • Use AWS Strands Agents: Building And Connecting Your First Model Context Protocol (MCP) Server to Optional.

Frequently asked questions

You need Git, Node.js v22.16.01+, npm/Yarn, Python 3.13.x, a pip/Poetry package manager, an AWS account (for Amazon Bedrock), and a free Shutterstock test account with an API token.