mcp-agent and sample-agentic-ai-demos
About mcp-agent
lastmile-ai/mcp-agent
Build effective agents using Model Context Protocol and simple workflow patterns
Fully implements MCP with automatic lifecycle management of server connections, and provides composable agent patterns (map-reduce, orchestrator, evaluator-optimizer, router) based on Anthropic's best practices. Scales from simple agents to production workflows via Temporal integration without API changes, enabling pause/resume/recovery capabilities. Supports the complete MCP specification including tools, resources, prompts, notifications, OAuth, and sampling.
About sample-agentic-ai-demos
aws-samples/sample-agentic-ai-demos
Collection of examples of how to use Model Context Protocol with AWS.
Demonstrates MCP integration patterns across multiple transport mechanisms (stdio and Server-Sent Events) and AI frameworks, with production-ready examples using Amazon Bedrock, Spring AI, and FastAPI deployed on ECS. Covers end-to-end agentic workflows including RAG with pgVector and tool-calling through MCP servers that handle domain logic like appointment management.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work