If the chief reason to use MCP is security, I'm sold: it's a dead letter, and we're not going to be using it a couple years from now.
Re:MCP Is Dead; Long Live MCP
by 0xbadcafebee on Sunday March 15, 2026 @12:15AM
(#47384302)
[delayed]
Re:MCP Is Dead; Long Live MCP
by DetroitThrow on Sunday March 15, 2026 @04:04AM
(#47385270)
>Among them, chief is security
Considering many popular MCPs have done auth incorrectly, this made me lol
> Among them, chief is security
The security is so chief that they had no security at all until several versions later when they hastily bolted on OAuth.
MCP is a vibe-codef protocol that rode one of the many AI hype waves where all "design documents" are post-hoc justifications.
They did the right thing in hindsight: leave security open until clear patterns emerge, then solidify those patterns into a spec. The spec is still in draft and currently, they are trying to find a simpler solution for client registration than DCR, which apparently ephemeral clients seems to solve for now.
If they had made the security spec without waiting for user information they would most certainly have chosen a suboptimal solution.
For any sufficiently complex set of AI tasks, you will eventually need to invent MCP. The article posted here talks about those cases and reasons. However, there are cases when you should not use MCP, and the article points those out too.