Sample Agentic AI Demos
Collection of examples of how to use Model Context Protocol with AWS.
What is Sample Agentic AI Demos?
Sample Agentic AI Demos is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to collection of examples of how to use model context protocol with aws.
Collection of examples of how to use Model Context Protocol with AWS.
This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Collection of examples of how to use Model Context Protocol
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx sample-agentic-ai-demosConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Sample Agentic AI Demos
Sample Agentic AI Demos is an AWS-maintained collection of reference implementations showing how to build Model Context Protocol servers and clients using AWS services. It includes Spring AI MCP servers deployed to Amazon ECS over Server-Sent Events, a FastAPI Python MCP server backed by Anthropic Bedrock, and a dog-adoption agent that combines PostgreSQL with pgVector for RAG and MCP for appointment scheduling — making it a practical learning resource for teams building production-grade agentic AI systems on AWS.
Prerequisites
- An AWS account with Amazon Bedrock enabled in your target region
- AWS CLI configured with credentials that have Bedrock, ECS, and ECR access
- Python 3.10+ and pip, or Java 17+ with Maven for the Spring AI samples
- Docker for building and pushing container images to ECS
- An MCP-compatible client such as Claude Desktop for local testing
Clone the repository
Clone the sample-agentic-ai-demos repository from AWS Samples. Each demo is in its own subdirectory with independent configuration.
git clone https://github.com/aws-samples/sample-agentic-ai-demos.git
cd sample-agentic-ai-demosChoose a demo and read its README
Navigate to the specific demo directory you want to run. Each subdirectory contains its own README with deployment instructions for that particular MCP server or client pattern.
ls -la # explore available demos
# Examples: spring-ai-mcp-ecs, fastapi-mcp-bedrock, dog-adoption-agentConfigure AWS credentials and Bedrock access
Ensure your AWS CLI is configured and that your IAM role has access to Amazon Bedrock's Converse API. Request model access in the Bedrock console if needed.
aws configure
# Verify Bedrock access:
aws bedrock list-foundation-models --region us-east-1 --output tableDeploy a FastAPI MCP server example
For the FastAPI-based MCP demo, install dependencies and run locally to test before deploying to ECS. Set your AWS region so Bedrock calls are routed correctly.
cd fastapi-mcp-bedrock # adjust to actual directory name
pip install -r requirements.txt
export AWS_REGION=us-east-1
uvicorn main:app --host 0.0.0.0 --port 8000Connect an MCP client to the running server
Configure Claude Desktop or another MCP client to connect to the running MCP server. For local testing use STDIO; for ECS deployments the server exposes an SSE endpoint behind an Application Load Balancer.
{
"mcpServers": {
"aws-bedrock-demo": {
"command": "python",
"args": ["/path/to/sample-agentic-ai-demos/fastapi-mcp-bedrock/main.py"]
}
}
}Sample Agentic AI Demos Examples
Client configuration
Example Claude Desktop configuration for a locally running AWS MCP demo server.
{
"mcpServers": {
"aws-bedrock-demo": {
"command": "python",
"args": ["/path/to/sample-agentic-ai-demos/fastapi-mcp-bedrock/main.py"],
"env": {
"AWS_REGION": "us-east-1"
}
}
}
}Prompts to try
Example interactions with the AWS agentic AI demo servers.
- "Book an adoption appointment for the golden retriever listed in the shelter database"
- "What AWS Bedrock models are available and what are their context window sizes?"
- "Use the MCP server to query the PostgreSQL database and find all available dogs under 2 years old"
- "Show me the appointment schedule for this week and check for conflicts"
- "Demonstrate how to call an MCP tool from a Bedrock agent using the Converse API"Troubleshooting Sample Agentic AI Demos
Bedrock API calls fail with AccessDeniedException
You must explicitly request access to foundation models in the Amazon Bedrock console under Model Access before they can be used. Navigate to Bedrock > Model Access in the AWS console and enable the models you need (e.g., Claude 3 Sonnet).
ECS deployment fails with ECR push errors
Authenticate Docker with ECR before pushing: aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin <account_id>.dkr.ecr.us-east-1.amazonaws.com. Ensure your IAM role has ecr:GetAuthorizationToken and ecr:PutImage permissions.
SSE connection to ECS-deployed server times out
Check that the Application Load Balancer's idle timeout is set high enough for SSE connections (minimum 60 seconds, recommended 300+). Also verify the security group allows inbound traffic on port 80/443 from your client IP.
Frequently Asked Questions about Sample Agentic AI Demos
What is Sample Agentic AI Demos?
Sample Agentic AI Demos is a Model Context Protocol (MCP) server that collection of examples of how to use model context protocol with aws. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Sample Agentic AI Demos?
Follow the installation instructions on the Sample Agentic AI Demos GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Sample Agentic AI Demos?
Sample Agentic AI Demos works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Sample Agentic AI Demos free to use?
Yes, Sample Agentic AI Demos is open source and available under the MIT-0 license. You can use it freely in both personal and commercial projects.
Sample Agentic AI Demos Alternatives — Similar Coding Agents Servers
Looking for alternatives to Sample Agentic AI Demos? Here are other popular coding agents servers you can use with Claude, Cursor, and VS Code.
Dify
★ 142.2kProduction-ready platform for agentic workflow development.
Ruflo
★ 54.0k🌊 The leading agent orchestration platform for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features enterprise-grade architecture, self-learning swarm intelligence, RAG integrat
Goose
★ 45.7kan open source, extensible AI agent that goes beyond code suggestions - install, execute, edit, and test with any LLM
Antigravity Awesome Skills
★ 38.3kInstallable GitHub library of 1,400+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes installer CLI, bundles, workflows, and official/community skill collections.
AgentScope
★ 25.5kBuild and run agents you can see, understand and trust.
Serena
★ 24.5kA coding agent toolkit that provides IDE-like semantic code retrieval and editing tools, enabling LLMs to efficiently navigate and modify codebases using symbol-level operations instead of basic file reading and string replacements.
Browse More Coding Agents MCP Servers
Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Sample Agentic AI Demos in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Sample Agentic AI Demos?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.