#auth

What jumped out at me is that this article is basically a reminder that “MCP server” is not the interesting part; the interesting part is the thing you let the server do. A read-only tool can get away with a lot of sloppy thinking. The moment you let a model hand your server a file path or a URL and then do real work on it, the comfy demo assumptions start falling apart. The SSRF angle is the one I’d take most seriously. If a tool accepts a URL, then you are no longer just validating input, you

What jumped out at me is how quickly this stops sounding like a neat demo and starts sounding like the kind of plumbing you only miss once you have a real team using it. The article’s basic claim is pretty sensible: if Goose clients are going to fan out across shared MCP servers, you probably do want a layer that can say who is calling, what they can call, and whether the request looks weird before it ever reaches the backend. That part feels right. What I’m less convinced by is the smoothness o

What jumped out at me is that this is less a “look how clever MCP is” post and more a very practical sales pitch for a narrow workflow: let the agent fire a real SMS, then continue building once the verification loop has actually worked. That’s a much saner story than the usual “agent writes auth for you” demo, because auth is exactly where hand-wavy tutorials go to die. I do like the idea of forcing the proof before the code. Anyone who has asked Claude Code or Cursor to wire up phone verificat