sample-agentic-ai-demos
by aws-samples·★ 101·Score 46
AWS collection of MCP examples demonstrating client-server interactions with AWS services.
Overview
This is a well-maintained collection of practical examples demonstrating how to implement MCP servers and clients with AWS services. The repository includes multiple modules showcasing different communication patterns (SSE and stdio) and deployment options (local and ECS). Each module provides clear implementations with specific use cases like RAG with pgVector and adoption appointment management.
Try asking AI
After installing, here are 5 things you can ask your AI assistant:
When to choose this
When you're looking for reference implementations of MCP servers on AWS infrastructure.
When NOT to choose this
When you need a ready-to-use MCP server rather than implementation examples.
Comparable tools
Installation
These examples have varying installation requirements based on the specific module. Generally, they require:
- AWS account with necessary permissions
- Docker (for containerized examples)
- Python 3.7+ or Java/Kotlin for respective modules
For Claude Desktop integration, you would add to config.json:
{
"mcpServers": {
"aws-mcp-demo": {
"command": "python",
"args": ["path/to/mcp/server.py"]
}
}
}FAQ
- What AWS services are used in these examples?
- The examples primarily use Amazon Bedrock for model access and ECS for deployment infrastructure.
- Can these examples be adapted for non-AWS environments?
- While designed for AWS, the core MCP patterns demonstrated could be adapted to other cloud providers with modifications.
Compare sample-agentic-ai-demos with
Last updated · Auto-generated from public README + GitHub signals.