Hacker News Reader

Comment by dennisy | Hacker News Reader

Oh very intriguing! Could you please elaborate how you are using MCP servers with VS code for coding?

Personally I'm using the Filesystem server along with the mcp server called wcgw[0] that provides a FileEdit action. I use MacWhisper[1] to dictate. I use `tree` to give Claude a map of the directory I'm interested in editing. I usually opt to run terminal commands myself for better control though wcgw does that too. I keep the repo open in a Cursor/Windsurf window for other edits I need.

But other than that I basically just tell the model what I want to do and it does it, lol. I like the Claude Desktop App interface better than trying to do things in Cursor/Windsurf directly, I like the ability to organize prompts/conversations in terms of projects and easily include context. I also honestly just have a funny feeling that the Claude web app often performs better than the API responses I get from the IDEs.

[0] https://github.com/rusiaaman/wcgw

[1] https://goodsnooze.gumroad.com/l/macwhisper

Just use the Filesystem MCP Server, and give it access to the repo you're working on:

https://github.com/modelcontextprotocol/servers/tree/main/sr...

This way you will still be in control of commits and pushes.

So far I've used this to understand parts of a code base, and to make edits to a folder of markdown files.

how is that better than AI Coding tools? They do more sophisticated things such as creating compressed representations of the code that fit better into the context window. E.g https://aider.chat/docs/repomap.html.

Also they can use multiple models for different tasks, Cursor does this, so can Aider: https://aider.chat/2024/09/26/architect.html

I answered a comment asking how to do it.

I didn't say it was better!

fair point

I have never found embeddings to be that helpful, or context beyond 30-50K tokens to be used well by the models. I think I get better results by providing only the context I know for sure is relevant, and explaining why I'm providing it. Perhaps if you have a bunch of boilerplate documentation that you need to pattern-match on it can be helpful, but generally I try to only give the models tasks that can be contextualized by < 15-20 medium code files or pages of documentation.

Reply on news.ycombinator.com