Sample Agentic Ai Demos
What is Sample Agentic Ai Demos
Agentic AI is a framework designed for building intelligent agents that can interact with users and systems through various protocols, particularly the Model Context Protocol (MCP). It utilizes AWS services to enable advanced functionalities such as real-time communication and integration with machine learning models, enhancing the user experience in applications like customer support, virtual assistants, and more.
Use cases
Common use cases for Agentic AI include creating chatbots for customer service, personal assistants that manage tasks, agents for managing appointments or reservations, and applications that require data retrieval from databases using retrieval-augmented generation (RAG). These agents can be deployed in various industries, including healthcare, e-commerce, and hospitality.
How to use
To use Agentic AI, developers can select from various modules provided in the repository. Each module demonstrates a different implementation of the MCP protocol, utilizing different technologies such as FastAPI, Spring AI, and Docker for deploying server-client architectures. Following the guidelines in each module, users can set up their environments, run sample applications, and extend functionality based on their requirements.
Key features
Key features of Agentic AI include real-time communication via Server-Sent Events (SSE), compatibility with multiple programming languages and frameworks, the ability to integrate with AWS services like Bedrock for machine learning capabilities, and structured handling of user interactions through the Model Context Protocol. This makes it a flexible solution adaptable for various applications.
Where to use
Agentic AI can be deployed in cloud environments, particularly within AWS infrastructure, utilizing services such as Amazon ECS for container orchestration, or AWS Fargate for serverless application deployment. It’s suitable for businesses looking to enhance their digital interfaces, improve user engagement, and leverage AI capabilities for automated responses and decision-making support.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Overview
What is Sample Agentic Ai Demos
Agentic AI is a framework designed for building intelligent agents that can interact with users and systems through various protocols, particularly the Model Context Protocol (MCP). It utilizes AWS services to enable advanced functionalities such as real-time communication and integration with machine learning models, enhancing the user experience in applications like customer support, virtual assistants, and more.
Use cases
Common use cases for Agentic AI include creating chatbots for customer service, personal assistants that manage tasks, agents for managing appointments or reservations, and applications that require data retrieval from databases using retrieval-augmented generation (RAG). These agents can be deployed in various industries, including healthcare, e-commerce, and hospitality.
How to use
To use Agentic AI, developers can select from various modules provided in the repository. Each module demonstrates a different implementation of the MCP protocol, utilizing different technologies such as FastAPI, Spring AI, and Docker for deploying server-client architectures. Following the guidelines in each module, users can set up their environments, run sample applications, and extend functionality based on their requirements.
Key features
Key features of Agentic AI include real-time communication via Server-Sent Events (SSE), compatibility with multiple programming languages and frameworks, the ability to integrate with AWS services like Bedrock for machine learning capabilities, and structured handling of user interactions through the Model Context Protocol. This makes it a flexible solution adaptable for various applications.
Where to use
Agentic AI can be deployed in cloud environments, particularly within AWS infrastructure, utilizing services such as Amazon ECS for container orchestration, or AWS Fargate for serverless application deployment. It’s suitable for businesses looking to enhance their digital interfaces, improve user engagement, and leverage AI capabilities for automated responses and decision-making support.
Clients Supporting MCP
The following are the main client software that supports the Model Context Protocol. Click the link to visit the official website for more information.
Content
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.
Dev Tools Supporting MCP
The following are the main code editors that support the Model Context Protocol. Click the link to visit the official website for more information.
