A Critical Look at MCP

Re:A Critical Look at MCP by dend on Saturday May 10, 2025 @03:43PM (#43948313)

Just to add one piece of clarification - the comment around authorization is a bit out-of-date. We've worked closely with Anthropic and the broader security community to update that part of MCP and implement a proper separation between resource server (RS) and authorization server (AS) when it comes to roles. You can see this spec in draft[1] (it will be there until a new protocol version is ratified).

[1]: https://modelcontextprotocol.io/specification/draft/basic/au...

[ Parent | on HN ]

Re:A Critical Look at MCP by _raz on Saturday May 10, 2025 @04:03PM (#43948495)

Idk, I'm kind of agnostic and ended up throwing it in there.

Regurgitating the OAuth draft don't seem that usefull imho, and why am I forced into it if I'm using http. Seems like there are plenty of usecases where un-attended thing would like to interact over http, where we usually use other things aside from OAuth.

It all probably could have been replaced by

- The Client shall implement OAuth2 - The Server may implement OAuth2

[ Parent | on HN ]

Re:A Critical Look at MCP by dend on Saturday May 10, 2025 @05:03PM (#43948986)

For local servers this doesn't matter as much. For remote servers - you won't really have any serious MCP servers without auth, and you want to have some level setting done between client and servers. OAuth 2.1 is a good middle ground.

That's also where, with the new spec, you don't actually need to implement anything from scratch. Server issues a 401 with WWW-Authenticate, pointing to metadata for authorization server locations. Client takes that and does discovery, followed by OAuth flow (clients can use many libraries for that). You don't need to implement your own OAuth server.

[ Parent | on HN ]

Re:A Critical Look at MCP by vlovich123 on Saturday May 10, 2025 @05:53PM (#43949308)

Bearer tokens work elsewhere and imho are drastically simpler than oauth

[ Parent | on HN ]

Re:A Critical Look at MCP by dend on Sunday May 11, 2025 @12:41AM (#43951443)

But where would you get bearer tokens? How would you manage consent and scopes? What about revocation? OAuth is essentially the "engine" that gives you the bearer tokens you need for authorization.

[ Parent | on HN ]

Re:A Critical Look at MCP by lolinder on Saturday May 10, 2025 @06:05PM (#43949392)

What percentage of the MCP spec is (was?) LLM output?

It's setting off all kinds of alarm bells for me, and I'm wondering if I'm on to something or if my LLM-detector alarms are miscalibrated.

[ Parent | on HN ]

Re:A Critical Look at MCP by dend on Sunday May 11, 2025 @12:41AM (#43951439)

Can only speak for the authorization spec, where I am actively participating - zero. The entire spec was written, reviewed, re-written, and edited by real people, with real security backgrounds, without leaning into LLM-based generation.

[ Parent | on HN ]

Re:A Critical Look at MCP by _kidlike on Sunday May 11, 2025 @02:08AM (#43951770)

I know it's not auth-related, but the main MCP "spec" says that it was inspired by LSP (language server protocol). Wouldn't something like HATEOAS be more apt?

[ Parent | on HN ]