{"author":{"name":"Evandro Franco","slug":"evandro-franco","article_count":1,"latest_published_at":"2026-04-18T19:22:44.629+00:00","profile_url":"https://vff.ai/authors/evandro-franco","api_url":"https://vff.ai/api/authors/evandro-franco"},"articles":[{"slug":"introducing-stateful-mcp-client-capabilities-on-amazon-bedrock-agentcore-runtime","title":"Bedrock AgentCore adds stateful MCP for interactive agent workflows","url":"https://vff.ai/article/2026/04/18/introducing-stateful-mcp-client-capabilities-on-amazon-bedrock-agentcore-runtime","content_type":"aggregated_news","summary":"Amazon Bedrock AgentCore Runtime now supports stateful Model Context Protocol (MCP) client capabilities, enabling AI agents to pause execution for user input, request LLM-generated content, and stream real-time progress updates. Previously, stateless MCP implementations could only execute one-way tool calls without bidirectional communication. The update introduces three new capabilities: elicitation for mid-execution user requests, sampling for dynamic LLM content generation, and progress notification for long-running tasks. Stateful mode provisions dedicated microVMs per user session with up to 8 hours persistence, maintaining conversation continuity through session identifiers.","published_at":"2026-04-18T19:22:44.629+00:00","updated_at":"2026-04-22T00:59:04.768177+00:00","source":{"url":"https://aws.amazon.com/blogs/machine-learning/introducing-stateful-mcp-client-capabilities-on-amazon-bedrock-agentcore-runtime/","name":"AWS Machine Learning Blog"},"featured_image":{"url":"https://miro.medium.com/0*Av5Uzs125GHYydh9.png","alt":null},"categories":[{"name":"AI Agents","slug":"ai-agents"},{"name":"Infrastructure","slug":"infrastructure"},{"name":"Coding / Dev Tools","slug":"coding-dev-tools"}]}]}