sample-ecs-mcp-server
Verified Safeby aws-samples
Overview
Deployment of an Agentic AI architecture on AWS Fargate using Amazon ECS, connecting to multiple Model Context Protocol (MCP) servers for tool execution.
Installation
npm run cdk deployEnvironment Variables
- MCP_SERVICE_ONE_NAME
- MCP_SERVICE_ONE_PORT
- MCP_SERVICE_TWO_NAME
- MCP_SERVICE_TWO_PORT
Security Notes
The architecture uses AWS Secrets Manager for the API key, and service-to-service communication employs Service Connect for private networking. IAM policies for Bedrock model invocation and S3 bucket listing, while using a wildcard resource (`*`), are explicitly justified for the sample's functionality. The Application Load Balancer is internet-facing, allowing HTTP access from any IPv4 address, which is noted but expected for a public API endpoint.
Similar Servers
mcp-k8s-go
An MCP server enabling AI assistants and users to interact with and manage Kubernetes clusters by listing, getting, applying, and executing commands on Kubernetes resources.
sample-serverless-mcp-servers
Demonstrates a stateful Model Context Protocol (MCP) server implementation using Python and FastMCP, deployed on AWS ECS Fargate, providing a simple echo functionality.
sample-agentic-ai-demos
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.
mcpc
A framework for building agentic Model Context Protocol (MCP) servers by composing existing MCP tools. It enables the creation of portable, interoperable AI agents with flexible execution modes and robust logging/tracing capabilities.