AI Agents with MCP: Model Context Protocol for Building Clients, Servers, and End-To-End Agents
暫譯: 使用 MCP 建構 AI 代理：用於打造用戶端、伺服器與端到端代理的 Model Context Protocol

Since its release in late 2024, Anthropic's Model Context Protocol (MCP) has redefined how developers build and connect AI agents to tools, data, and each other. AI Agents with MCP is the first comprehensive guide to this rapidly emerging standard, helping engineers unlock its full potential with hands-on projects. Whether you're developing agentic workflows, bridging tools across platforms, or creating robust multiagent systems, this book walks you through every layer of MCP--from protocol structure to server and client implementation.

Author Kyle Stratis provides the practical expertise needed to build fully functional MCP servers, clients, and more. Unlike high-level overviews or fragmented documentation, this book gives you a deep systems-level understanding of MCP's capabilities--and limitations. With its flexible, model-agnostic design, MCP continues to gain traction across the generative AI community; this book ensures you're ready to build with it confidently and effectively.

• Understand the structure and core concepts of the Model Context Protocol
• Build complete MCP servers, clients, and transport layers in Python
• Consume tools, prompts, and data via MCP-based agent workflows
• Extend agent capabilities with MCP for large-scale and AI-native systems