What MCP actually changes about tool integration
The Model Context Protocol is often described as USB-C for AI tools. The more useful framing is that it moves the integration boundary.
Writing
Notes on things I have had to work out, mostly about getting AI systems to behave in production.
Training/serving skew is a plumbing problem
The gap between how a feature is computed in training and how it is computed at inference is rarely a modelling failure. It is two codepaths.