Live data from Hacker News

I still prefer MCP over skills

david.coffee

411–415 of 415 posts

Re: I still prefer MCP over skills

#411

Earlier quoted context omitted.

This is exactly what I do too. Works very well. I have a whole bunch of scripts and cli tools that claude can use, most of them was built by claude too. I very rarely need to use my IDE because of this, as I've replicated some of Jetbrains refactorings so claude doens't have to burn tokens to do the same work. It also turns a 5 minute claude session into a 10 second one, as the scripts/tools are purpose made. Its rea…

This is a great idea. Did you happen to release the source for this? I run into this all the time!

Nope, I just dump it all in a folder (~/scripts) that claude can read & it picks them up as skills. A good chunk of them are regex based, many are find/replace type tools, some are small code generators & template inflators, some are deployment tools, some are audit tools. I cannot release them at this time, most of them are specific to our company, infra and codebase (main codebase is 1MLoC), sorry about that.

Start with a simple "Let me build a script for claude that can rename the namespace for all the file in a folder". If you have 100K+ plus files, it effort is worth it and your tools start getting chained together too. So make sure each tool only has one purpose for existing and that its output is perfect. So when claude start chaining them and you see what is possible, the mind opens up even more to possibilities.

Re: I still prefer MCP over skills

#412
post #406

Earlier quoted context omitted.

> I've replicated some of Jetbrains refactorings How? Jetbrains in a Java code baes is amazing and very thorough on refactors. I can reliably rename, change signature, move things around etc.

Typically by deeply misunderstanding what those refactoring tools actually do

What is so magical about it? Most of them are pretty straight forward and core functionality easy to replicate in 30 minutes or less?

Re: I still prefer MCP over skills

#413

Earlier quoted context omitted.

This has been hashed to death and back. The mcp allows a separation between the agent and the world, at its most basic not giving the agent your token or changing a http header , forcing a parameter. Well yes you don’t need those things all the time and who knows if the inventor of mcp had this idea in mind but here we are

The separation is being oversold as if only MCP can do it, which is laughable. Any CLI can trivially do exactly what MCP do in terms of separation.

How ? Have you used these things when they are blocked and try to get around the block

Re: I still prefer MCP over skills

#414
post #10

I could not agree any less with the author. I don’t want APIs, I want agents to use the same CLI tooling I already use that is locally available. If my agents are using CLI tooling anyways there is no need to add an extra layer via MCP. I don’t want remote MCP calls, I don’t even want remote models but that’s cost prohibitive. If I need to call an API, a skill with existing CLI tooling is more than capable.

I keep getting hung up on securely storing and using secrets with CLI vs MCP. With MCP, you can run the server before you run the agent, so the agent never even has the keys in its environment. That way. If the agent decides to install the wrong npm package that auto dumps every secret it can find, you are less likely to have it sitting around. I haven’t figured out a good way to guarantee that with CLIs.

Just wrap it with a script that handles the auth for you and the AI doesnt realize auth is even needed. I put my creds in ~/.config/ and write bash wrappers that read those and proxy the values into the api calls as needed.

Re: I still prefer MCP over skills

#415

Don't focus on what you prefer: it does not matter. Focus on what tool the LLM requires to do its work in the best way. MCP adds friction, imagine doing yourself the work using the average MCP server. However, skills alone are not sufficient if you want, for instance, creating the ability for LLMs to instrument a complicated system. Work in two steps: 1. Ask the LLM to build a tool, under your guide and specification…

It makes a lot of sense to use an MCP for git and everything else if you want observability across many users. It gives you a place to shim security controls, monitoring, and alerting into the tool call pipeline.
Post reply on HN