Sample Model Context Protocol Demos
LocalAbout Sample Model Context Protocol Demos
A collection of sample projects showing how to build agentic AI on AWS with Model Context Protocol. It is aimed at developers who want reference deployments using Amazon Bedrock.
Key features
- 01Bedrock Converse API client examples
- 02MCP over stdio and SSE transports
- 03Container deployments on ECS
- 04pgvector RAG combined with MCP server
Use cases
- 01Running a local Bedrock client against an MCP stdio server
- 02Deploying MCP servers and agents on ECS
- 03Building an agent with RAG and appointment management
MCP support
The samples include MCP servers and clients that communicate over stdio or SSE.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAgentic 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.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.