Re:A Critical Look at MCP
by practal on Saturday May 10, 2025 @03:26PM
(#43948171)
The difficult part is figuring out what kind of abstractions we need MCP servers / clients to support. The transport layer is really not important, so until that is settled, just use the Python / TypeScript SDK.
[ Parent
| on HN ]
But the spec is on the transport level. So for the specification, the transport layer is very important.
This is the spec that counts: https://github.com/modelcontextprotocol/modelcontextprotocol...
How exactly those messages get transported is not really relevant for implementing an mcp server, and easy to switch, as long as there is some standard.
Re:A Critical Look at MCP
by vlovich123 on Saturday May 10, 2025 @06:01PM
(#43949355)
You’re ignoring the power of network effects - “shitty but widely adopted” makes “better but just starting adoption harder” to grow. Think about how long it takes to create a new HTTP standard - we’ve had 3 HTTP standards in the past 30 years, the first 19 of which so no major changes. HTTP/2 kind of saw no adoption in practice and HTTP/3 is still a mixed bag. In fact, most of the servers pretend HTTP/1 with layers in front converting the protocols.
Underestimate network effects and ossification at your own peril.