News for hackers. Stuff that matters.
Re:OpenCode Browse by jgilias on Tuesday November 17, 2026 @02:03AM (#50528351)
You forgot the main one:

- they necessarily work through the context window and therefore don’t compose;

Meaning, if your agent has a skill that needs to run five MCP tools in a certain way, it can’t just script that away the first time it sees this, and have that flow be fast and token efficient from then on.

MCPs are a 2025 tech meant to solve 2025 AI problems.

Re:OpenCode Browse by insin on Tuesday November 17, 2026 @05:18AM (#50529596)
If your harness can't compose tool calls or direct results of them to outside of context, you have a harness problem, not an MCP problem
Re:OpenCode Browse by jgilias on Tuesday November 17, 2026 @10:00AM (#50532290)
Can you elaborate a bit how that works?
Re:OpenCode Browse by anthonypasq on Tuesday November 17, 2026 @10:15AM (#50532507)
https://blog.cloudflare.com/code-mode

funny, because you are complaining about limitations of MCP that have been solved since 2025

Re:OpenCode Browse by jgilias on Tuesday November 17, 2026 @10:56AM (#50533196)
Turning Model Context Protocol endpoints into an API such that they can be composed proves the point. And that’s not something that can be done in the general case as machine interpretable output is optional in the protocol.
Re:OpenCode Browse by anthonypasq on Tuesday November 17, 2026 @01:24PM (#50535877)
> Turning Model Context Protocol endpoints into an API such that they can be composed proves the point.

which point exactly?