mcp-agent and agent-mcp
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 agent-mcp
grupa-ai/agent-mcp
MCPAgent for Grupa.AI Multi-agent Collaboration Network (MACNET) with Model Context Protocol (MCP) capabilities baked in
Implements a decorator-based abstraction layer that translates between diverse AI agent frameworks (Autogen, LangGraph, LangChain, CrewAI, etc.) into a unified MCP protocol, enabling seamless cross-framework collaboration. The system provides automatic provider routing and cost optimization across multiple LLM providers, alongside built-in discovery, authentication, and task coordination mechanisms. AgentMCP targets MACNet—a decentralized network for agent-to-agent collaboration—while supporting both synchronous and asynchronous operations via FastAPI's infrastructure.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work