VFF - The signal in the noise
News

Bedrock AgentCore adds stateful MCP for interactive agent workflows

Read original
Share
Bedrock AgentCore adds stateful MCP for interactive agent workflows

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.

  • Bedrock AgentCore Runtime adds stateful MCP support, enabling interactive multi-turn agent workflows that can pause for user input or LLM sampling
  • Three new client capabilities: elicitation (request user input), sampling (request LLM content), and progress notification (stream real-time updates)
  • Stateful mode provisions isolated microVMs per session lasting up to 8 hours, replacing stateless HTTP model that couldn't maintain conversation context
  • Completes bidirectional MCP protocol implementation, allowing servers to initiate requests back to clients rather than only responding to tool calls

Stateful MCP support removes a fundamental constraint in agent design: the inability to maintain conversation threads or request clarification mid-execution. This capability gap has forced developers to work around limitations in long-running workflows, interactive debugging, and real-time feedback loops. The addition brings MCP implementations closer to practical agent requirements where workflows often need human-in-the-loop validation or dynamic content generation during execution.

For operators building production agents, stateful MCP unlocks use cases that require interactive workflows, such as approval gates, clarification requests, or progress reporting during extended operations. This reduces the need for custom workarounds and external orchestration layers, lowering development complexity and time-to-market for agent applications. The 8-hour session persistence and isolated microVMs provide a managed alternative to self-hosted MCP infrastructure.

  • Developers can now build agents that pause mid-execution for user input or LLM sampling, enabling interactive workflows previously impossible with stateless implementations
  • Session-based architecture with dedicated microVMs per user creates isolation and state persistence, but introduces operational considerations around resource allocation and session lifecycle management
  • Bidirectional MCP protocol support positions Bedrock as a more complete MCP runtime, potentially increasing adoption among developers already invested in the open standard
  • The 8-hour session limit and 15-minute idle timeout create practical constraints for long-running or intermittent workflows that may require external session management

Monitor adoption patterns to see which use cases drive stateful MCP demand and whether the session timeout windows prove sufficient for real-world workflows. Watch for competing implementations from other cloud providers or open-source projects that may offer different session persistence models. Track whether the bidirectional protocol capabilities become table stakes for agent platforms or remain a differentiator.

OneUpAI
OneUp Your Business. Get More Done. OneUp Your Business. Get More Done. OneUp Your Business. Get More Done.
Learn More
Share

Subscribe to the newsletter

The latest stories and analysis, delivered to your inbox.

Free. No spam. Unsubscribe any time.

Related stories

MIT Researcher Uses GPT-5.6 Sol to Automate Quantum Experiments

MIT Researcher Uses GPT-5.6 Sol to Automate Quantum Experiments

An MIT researcher is using GPT-5.6 Sol with Codex to autonomously run quantum computing experiments, including analyzing results and calibrating qubits. The application demonstrates AI's capability to handle complex, iterative scientific workflows without human intervention. This represents a practical use case for large language models in experimental physics and quantum research.

· OpenAI
OpenAI Claims Solution to 90-Year-Old Math Problem
TrendingNews

OpenAI Claims Solution to 90-Year-Old Math Problem

OpenAI announced it has solved the Navier-Stokes problem, a 90-year-old mathematical challenge, using an internal AI model more powerful than GPT-6 Astra and 10,000 concurrent agents. The Navier-Stokes problem is one of seven Millennium Prize Problems, each offering a $1 million reward. OpenAI began training the model on August 28th and claims it has exhibited unprecedented capabilities in solving the fluid dynamics equations.

by Emma Roth· The Verge AI
AWS Adds Automated Quality Gates for AI Agents in CI/CD

AWS Adds Automated Quality Gates for AI Agents in CI/CD

AWS has published a technical guide for building a CI/CD quality gate that automatically evaluates AI agents deployed on Amazon Bedrock AgentCore runtime and blocks pull requests when performance regresses. The post covers a complete reference implementation including agent deployment, MCP server integration with OAuth protection, role-based access control, and automated evaluation using the AgentCore Evaluate API. The approach uses GitHub Actions to run on-demand evaluations with built-in LLM-based scorers that assess agent behavior across dimensions like helpfulness and tool selection accuracy.

by Mahsa Paknezhad· AWS Machine Learning Blog
Meta launches Muse to compete in AI agent race
TrendingModel Release

Meta launches Muse to compete in AI agent race

Meta has launched Muse, a personal AI agent designed to handle everyday tasks like online shopping, email, and trip planning with minimal user input. The product represents Meta's latest effort to regain ground in the competitive AI market against OpenAI, Anthropic, and Google. Muse can operate autonomously once given a goal, including opening browsers, filling forms, and negotiating on behalf of users.

by Robert Hart· The Verge AI