Home icon

Open Protocols for Agent Interoperability Part 3: Strands Agents & MCP

Open Source Blog



This article discusses open protocols for AI agent interoperability, focusing on using Strands Agents SDK and Model Context Protocol (MCP) to create interconnected agents.

  • Demonstrates building an HR agent system with multiple interconnected agents using Python
  • Shows how agents can communicate and share information using MCP
  • Highlights multi-turn inference capabilities with AI models and tools
  • Explains how to expose agents as MCP servers for inter-agent communication
  • Describes running agents on AWS using containers and serverless technologies

AWS has contributed two key enhancements to the MCP specification: Elicitation (allowing agents to request additional input) and Structured Output Schemas (enabling type-safe data transformations).



Go to article

The AWS News Feed is currently looking for gold sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.

Related articles

May 20
2025
Open Protocols for Agent Interoperability Part 1: Inter-Agent Communication on MCP
Jun 26
2025
Open Protocols for Agent Interoperability Part 2: Authentication on MCP
Jul 16
2026
Open Protocols with the Strands Agents SDK
Aug 21
2025
Open Protocols for Agent Interoperability Part 4: Inter-Agent Communication on A2A

The AWS News Feed is currently looking for silver sponsors. If you want to support the AWS community and reach a large audience of AWS professionals, consider sponsoring the AWS News Feed.