Introducing stateful MCP client capabilities on Amazon Bedrock AgentCore Runtime
Amazon Bedrock just shipped stateful MCP client capabilities. Here's why agents that remember context matter.

Why it matters
AWS is expanding Bedrock's agent runtime to support stateful Model Context Protocol servers, enabling agents to maintain context, request user input, and stream long-running task updates—a critical capability gap for production AI agent deployment.
The key facts
4 to knowAmazon Bedrock AgentCore Runtime now supports stateful MCP servers
New capabilities: user input requests during execution, LLM sampling for dynamic content, progress streaming for long-running tasks
Code examples and deployment guidance provided
Feature addresses agent context persistence and interactivity requirements
Go to the source
AWS Machine Learning Blogaws.amazon.com
Publisher excerpt: In this post, you will learn how to build stateful MCP servers that request user input during execution, invoke LLM sampling for dynamic content generation, and stream progress updates for long-running tasks. You will see code examples for each capability and deploy a working stateful MCP server to…
