News for hackers. Stuff that matters.
Re:Stateless MCP has recaptured my interest by bloppe on Wednesday August 05, 2026 @02:57PM (#49187330)
I guarantee you any LLM will be perfectly capable of navigating HTTP auth [1] which has been around since 1999.

You could use `curl`, or you could bake an HTTP client tool into the agent harness which operates at a more abstract level. The agent would just have a tool that looks a lot like the Fetch API [2] and the harness could simply be configured to inject credentials using the various well-established patterns that have long existed, allow / deny certain methods, etc. The thing is, everything you can do with MCP could also simply be done with REST, so neither is inherently better than the other, I just don't like the proliferation of needless standards.

[1]: https://developer.mozilla.org/en-US/docs/Web/HTTP/Guides/Aut...

[2]: https://developer.mozilla.org/en-US/docs/Web/API/Fetch_API/U...

Re:Stateless MCP has recaptured my interest by brabel on Thursday August 06, 2026 @06:38AM (#49194929)
You can’t be seriously proposing HTTP auth (you probably mean basic auth??) as a solution!? Just hand your raw credentials to the LLM, what could go wrong?
Re:Stateless MCP has recaptured my interest by bloppe on Thursday August 06, 2026 @04:26PM (#49202011)
Letting the harness inject the credentials implies not exposing them to the LLM.

Besides, the current state of MCP authentication almost always involves just hard coding secrets in .claude/settings.json so it's not like that's doing a great job keeping the creds away from the LLM anyway. All I'm saying is that MCP auth offers no advantage.