Preface All example code has been uploaded to a Git repository. Feel free to clone it directly if needed: https://github.com/rainuxhe/mcp-examples Introduction MCP (Model Context Protocol) is a standardized protocol designed for managing context in large language model interactions. Its core objective is to establish a structured, controllable, and extensible semantic execution environment for models, enabling them to perform task scheduling, tool invocation, resource collaboration, and state persistence within a unified context management framework. This approach overcomes the limitations of traditional Prompt Engineering in multi-turn interactions, instruction composition, and behavioral stability. ...

Introduction In real business scenarios, tracing a request’s complete processing path in logs based on a tracking_id is a common requirement. However, FastAPI does not provide this functionality out of the box, so developers need to implement it themselves. This article introduces how to add a tracking_id to the entire request lifecycle based on contextvars and automatically record it in logs. What is contextvars Python 3.7 added a module contextvars to the standard library, which stands for “Context Variables”. It is typically used to implicitly pass some environmental information variables, similar to threading.local(). However, threading.local() is thread-specific, isolating data states between threads, while contextvars can be used in asynchronous coroutines within the asyncio ecosystem. PS: contextvars can not only be used in asynchronous coroutines but can also replace threading.local() in multi-threaded functions. ...