sample-agentic-ai-demos
Verified Safeby aws-samples
Overview
This MCP Server (TypeScript SSE demo) demonstrates an interactive chat interface with tool integration, powered by Amazon Bedrock, designed for agentic AI interactions via the Model Context Protocol (MCP/SSE). It provides tools to interact with AWS S3 and retrieve time information.
Installation
./modules/converse-client-server-sse-demo-docker/scripts/run.shEnvironment Variables
- AWS_ACCESS_KEY_ID
- AWS_SECRET_ACCESS_KEY
- AWS_REGION
- AWS_SESSION_TOKEN
Security Notes
AWS credentials are managed through environment variables, which is a good practice. Network configurations for deployment to ECS (as seen in other modules' CDK code) utilize security groups and load balancers. For the local Docker Compose setup, ports are exposed to the host for development. The `eval` command in the `run.sh` script is used safely for setting Docker environment variables, not for arbitrary user input.
Similar Servers
awesome-mcp-devtools
This repository provides a curated list of developer tools, SDKs, frameworks, libraries, utilities, and resources for working with Model Context Protocol (MCP) servers.
mcp-dotnet-samples
This MCP server enhances GitHub Copilot by providing a mechanism to search, retrieve, and manage custom instructions and agents from the awesome-copilot repository, allowing for personalized AI assistance in development workflows.
mcp-servers
Provides a curated collection of Model Context Protocol (MCP) server configurations to enable AI agents to interact with various developer tools and services.
Polymcp
A comprehensive toolkit and agent framework for building Model Context Protocol (MCP) servers and orchestrating them with Large Language Models (LLMs) across Python and TypeScript environments.