Model Context Protocol servers, multi-agent systems, and AI-powered tools
Repositories exploring the Model Context Protocol (MCP) ecosystem — from running MCP servers on AWS infrastructure to building multi-agent systems with Strands and Bedrock. Includes document extraction, generative BI, and practical MCP patterns.
Added support for Amazon SageMaker AI endpoints as a Model Provider in the Strands Agents SDK, enabling developers to use SageMaker-hosted models with the Strands Agents framework.
Hybrid document extraction architecture comparing Claude, BDA, and Textract for intelligent document processing.
View on GitHubAI-powered multi-agent data analytics platform using AWS Bedrock and Strands Agents SDK. Demonstrates generative BI with coordinated agent workflows.
View on GitHubMCP Server that uses SageMaker AI APIs to monitor and manage resources.
View on GitHubRunning an MCP Server on AWS Fargate on Amazon ECS. Production-ready pattern for hosting MCP servers on managed container infrastructure.
View on GitHubA simple implementation of MCP Client/Server architecture with HTTP SSE transport layer, dockerized.
View on GitHubLearning Llama Index usage on AWS — both with Amazon SageMaker and Amazon Bedrock.
View on GitHub