Agent Vault promises to solve the credential problem in AI agents with an open-source proxy. I ran it against my real setup, measured the friction, and found something uncomfortable: it solves *where* you store credentials, but not *when* and *how* an agent decides to use them. That's a different pr
I've been running MCP in production for weeks and the problem I found isn't in any Dev.to post. MCP assumes context doesn't change between calls. My agents live in contexts that mutate. Three bugs that passed every test and failed in prod in ways that took me days to understand.
Emacs has spent decades thinking about how to safely grant real system access to unaudited plugins. In 2025, the AI agent ecosystem has the exact same problem — and isn't even having the conversation.
I had a local MCP server running in 12 minutes. Minute 13 I just stared at the screen with no idea what to do next. This post is about that moment — and why MCP is the protocol everyone talks about but almost nobody actually understands.
32 years in the dev trenches. Here I write what I learned, what I broke, and what nobody tells you in the tutorials.
No spam. Unsubscribe anytime.