hands-on lab

Orchestrating AI Workflows with AWS Agent Squad and Model Context Protocol

Difficulty: Intermediate
Duration: Up to 1 hour
Students: 4
On average, students complete this lab in15m
Get guided in a real environmentPractice with a step-by-step scenario in a real, provisioned environment.
Learn and validateUse validations to check your solutions every step of the way.
See resultsTrack your knowledge and monitor your progress.

Description

AWS Agent Squad is an open-source orchestration framework for building multi-agent systems where a supervisor agent coordinates a team of specialized worker agents. Workers operate with a narrow system prompt scoped to a single responsibility, and the supervisor handles breaking the request into sub-tasks, delegating each to the appropriate worker, and synthesizing the final response. Agent Squad exposes each worker to the supervisor as a callable tool, enabling structured collaboration across agents without shared state or overlapping logic.

Model Context Protocol (MCP) is an open standard that defines how agents connect to external tools and data sources over HTTP. An MCP server exposes a set of typed, callable tool functions that any compatible client can discover and invoke at runtime. This decouples tool logic from agent code so that workers can call tools on the MCP server without owning or packaging those tools themselves.

In this lab, you will deploy a supervisor agent that delegates to two specialized worker agents, build a stateless MCP tool server on Lambda that exposes product research tools, and trace the full delegation chain through the multi-agent workflow.

Learning objectives

Upon completion of this intermediate-level lab, you will be able to:

  • Design and implement a multi-agent system using AWS Agent Squad with a supervisor/worker pattern
  • Build and deploy a stateless Model Context Protocol (MCP) tool server on AWS Lambda
  • Integrate Agent Squad workers with the MCP tool server using the Strands MCP client

Intended audience

  • Candidates for the AWS Certified Generative AI Developer – Professional (AIP-C01) exam
  • Cloud Architects
  • AI Developers

Prerequisites

Familiarity with the following will be beneficial but is not required:

  • Strands Agent SDK
  • Amazon Bedrock
  • AWS Lambda

The following content can be used to fulfill the prerequisites:

Environment before

Environment after

Covered topics

Hands-on Lab UUID

Lab steps

0 of 6 steps completed.Use arrow keys to navigate between steps. Press Enter to go to a step if available.
  1. Logging In to the Amazon Web Services Console
  2. Introduction to Model Context Protocol (MCP)
  3. Configuring the MCP Tool Server
  4. Configuring the Research Worker Agent
  5. Configuring the Recommendation Worker Agent
  6. Configuring the Supervisor Agent