Agentic AI Samples
Collection of examples of how to build Agentic AI with AWS, including Model Context Protocol.
List of modules:
| Module | Lang | Description |
|---|---|---|
| Server Client MCP/SSE Demo | TypeScript | This full demo creates an Amazon Bedrock MCP client using the converse API and MCP server. The sample is deployed in containers that connect over MCP/SSE. |
| Server Client MCP/stdio Demo | Python | This is a demo Amazon Bedrock MCP client using the converse API and a simple MCP stdio server. The sample runs locally connected with Amazon Bedrock. |
| Server Client MCP/SSE on ECS | Spring AI & Kotlin | Provides a sample Spring AI MCP Server that runs on ECS; which is used by a Spring AI Agent using Bedrock; which also runs on ECS and is exposed publicly via a Load Balancer. |
| Server Client MCP/SSE in Bedrock Converse Client w/ pgVector RAG | Spring AI & Java | A Spring AI dog adoption agent built on Bedrock using PostgreSQL with pgvector for RAG, and an MCP Server for managing adoption appointments. |
| Server MCP/SSE on ECS | Spring AI & Kotlin | Very basic Spring AI MCP Server over SSE running on ECS. |
| MCP/SSE Server - FastAPI Client with Anthropic Bedrock | Python | An MCP SSE server with a FastAPI client that leverages Anthropic Bedrock. The sample runs on ECS Fargate with public access through an Application Load Balancer. |
Security
See CONTRIBUTING for more information.
License
This library is licensed under the MIT-0 License. See the LICENSE file.