MCP Mastery
About
AgentCore
Chapter 5
mid
~45 min

AgentCore Runtime

Package and deploy a LangGraph agent to managed runtime.

LangGraph ^0.4
Python >=3.11
runtime
observability
Reviewed 2026-05-16

Reading this chapter helps prevent 4 common multi-agent mistakes.

Overview

Package and deploy a LangGraph agent to managed runtime.

AgentCore Runtime architecture.

Key ideas

  • LangGraph owns orchestration: explicit state, nodes, and conditional edges.
  • AgentCore owns production concerns: runtime hosting, memory, identity, gateway, observability.
  • MCP standardizes tool surfaces so workers do not hard-code every backend integration.

Labs 4–9 in labs/agentcore/ follow a real AWS progression. Read the lab README for IAM and cost notes.

Walkthrough

  1. Model the workflow as a graph: who plans, who executes tools, who summarizes.
  2. Attach MCP tools through Gateway (or local mocks in early labs).
  3. Add Memory for session continuity and Identity before calling protected APIs.
  4. Instrument traces and run golden-set evals before promoting changes.

References

Quiz

  1. What is the primary focus of AgentCore Runtime?

  2. Which pattern routes work between specialized agents?

  3. Why expose tools through AgentCore Gateway?

← Supervisor Pattern in LangGraphAgentCore Memory →