Skip to content

Identity

I got 99 problems, but MCP got 1

Almost a year ago, while working on an open source project at Mozilla AI named mcpd (also a plugin system and proxy), I became frustrated in my dealings with the Model Context Protocol (MCP). So, like a good keyboard warrior, I wrote about it on the internet.

Since that time, a lot has changed in the fast-moving world of AI and with MCP. A few times over these months I thought: I should do a follow-up post, but then work got in the way. But fear not... the time has come.

MCP's Identity Crisis: When Security Theatre Meets Enterprise Reality

Update: November 2026

I've written a follow-up to this post. It corrects some things I got wrong here and covers what has changed in MCP since.

The Model Context Protocol (MCP) promises to be the "USB-C" of LLM integrations; simple, universal, and "extremely easy to build." Yet a fundamental disconnect exists between its security guidance and how authentication works in production systems. This isn't just a theoretical concern; it's creating an ecosystem where even official implementations can't follow the stated best practices.