• AWS Open Source Blog Open Protocols for Agent Interoperability Part 3: Strands Agents & MCP Developers are architecting and building systems of AI agents that work together to autonomously accomplish users’ tasks. • In Part 1 of our blog series on Open Protocols for Agent Interoperability we covered how Model Context Protocol (MCP) can be used to facilitate inter-agent communication and the MCP specification enhancements AWS is working on to enable that. • The examples in Part 1 used Spring AI and Java for building the agents and connecting them with MCP. • In Part 2 we discussed Authentication on MCP. • This is a critical aspect of connecting agents so they can work together in a larger system, all with knowledge of who the user is. • In Part 3 we will show how you can build inter-agent systems with the new Strands Agents SDK and MCP.
Article Summaries:
- AWS released the third installment of its “Open Protocols for Agent Interoperability” series, showcasing how the open‑source Strands Agents SDK can be combined with the Model Context Protocol (MCP) to build multi‑agent systems. The post demonstrates a simple HR‑assistant architecture in which a REST API exposes an HR agent that queries an employee‑info agent via MCP. The employee agent, built with Strands Agents and Amazon Bedrock, performs multi‑turn inference: it calls MCP tools to list skills, filters for AI‑related skills, retrieves matching employees, and returns the compiled list to the user. The example illustrates how agents can communicate, share data, and orchestrate tasks with minimal code.
Sources: