Before the whole "just use OpenAPI" crowd arrives, the point is that LLMs work better with curated context. An OpenAPI server not designed for that will quickly flood an LLM context window.
I guess there’s not really a good reason. Maybe there are specific constraints when working with LLMs? OpenAPI is quite verbose
Anyway, the technical merits don’t really matter. MCP (and any standard really) are only useful because they’re widely adopted. OpenAPI isn’t used for this, but MCP is. So, in practice, MCP is better for AI agents
it's so apt that one of the most common question/statements I hear is why not use OpenAPI? I don't know the answer. Or WTF is streaming HTTP? Sure feels like we're trying to reinvent web sockets. It must be either #notinventedhere or while the genius devs build the LLMs the interns do the documentation and SDKs
But to save you the click & read: it's OpenAPI for LLMs