News for hackers. Stuff that matters.

isaacrolandson

Re:Show HN: MCP Isn't Dead. You're Just Using It Wrong on Tuesday March 17, 2026 @12:24PM (#47414853)
tbh the whole code mode thing is actually kind of what were doing with commandable mcp.

The agent is essentially given a sandbox to write abitrary code against an API, with the users credentials for that api stored securly...

The pattern i assumed is that the agent would then 'save' this code as a tool to reuse later...

But youve got me thinking - maybe commandable should be more just like full code mode every time - every tool call be a new custom script written right then and executed immediately.

Maybe 'saving' those actions for later is just something the agent could do if it needs it more frequently...

hmmmmmm food for thought

Re:Show HN: MCP Isn't Dead. You're Just Using It Wrong on Tuesday March 17, 2026 @11:13AM (#47413842)
well its more of a protocol than an API isnt it? And it kind of works - especially if you use it properly!
Re:Show HN: MCP Isn't Dead. You're Just Using It Wrong on Tuesday March 17, 2026 @11:12AM (#47413827)
well if you read this you will know that progressive disclosure is actually now possible with MCP... well it always has been as a pattern in the spec - but claude code actually honours the spec as of Jan 2026... so there is no bloat baby

Show HN: MCP Isn't Dead. You're Just Using It Wrong

Everyone and their gran have been saying that MCP is dead.But could it be that MCP's saving grace has been with us all along - hiding in plain sight?A feature buried in Claude Code's Jan 2026 release may have marked the most powerful development in MCP since its inception - and almost nobody noticed. Dynamic Tool Registration.Dynamic tool registration extends an MCP server's abilities beyond...

( Read More... | 9 comments | 5 points | on HN )
Re:Codestral: Mistral's Code Model on Wednesday May 29, 2024 @03:23PM (#40515814)
Will this run on an M3 48GB?
Call me crazy but I prefer watching the original