> I have no idea what I'm missing.

    - Do you work in a team context of 10+ engineers?
    - Do you all use different agent harnesses?
    - Do you need to support the same behavior in ephemeral runtimes (GH Agents in Actions)?
    - Do you need to share common "canonical" docs across multiple repos?
    - Is it your objective to ensure a higher baseline of quality and output across the eng org?
    - Would your workload benefit from telemetry and visibility into tool activation?

What I want to know is what's the difference between a remote mcp and an api with an openapi.json endpoint for self-discovery? It's just as centralized

MCP is useful for the above. I work on my own more often than not and the utility of MCP goes far beyond the above. (see my other comment above).