MCP is eating the world

Obligatory note - if you're a backend developer, you do not need MCP. MCP is just tool/function calling. It has been around for a lot longer now. MCP is only needed if you need something to integrate with the frontend chat applications. If you need to automate something with LLMs, you do not need MCP. Right now, it's just the new cool buzzword to throw around.

AI coding tools have been improving/updating like craze over the past six months.

Honest question: what are some of the AI Dev tools (I prefer command line) that have leapt ahead recently, with good tool/function calling? Do you (or others) have a clear preference for Claude Code vs aider vs some other alternative? Or is the meta shifting toward the orchestrators like Taskmaster and Puppeteer?

I meant to say that MCP is just a wrapper around good old function/tool calling, it's not a new superpower by itself. So, if you're designing a Saas, you don't need to use MCP yourself, you can just use good old function/tool calling.

To answer your specific queries, I use the autocomplete in VS Code and I directly chat with ChatGPT-o3 for advanced problems because my background is in Elixir and most models that are hyped up fail badly with Elixir. I'm always a huge fan of o3 as it can solve the most complex problems I throw at it..

This is a really nifty CLI tool that lets you fit an LLM into a shell environment. Check out examples like piping context into and out of the `llm` command.

https://github.com/simonw/llm

Yes, but if I'm implementing "good old function/tool calling" today, why would I not implement it as MCP? I suppose it complicates things? MCP, in addition to being tooling endpoints, would also open up my software to a rapidly growing ecosystem that requires minimal additional work.

AND I can still use those same endpoints as tools. What would be the argument for "you don't need MCP when implementing new stuff"?

You don't need to use RESTful JSON to get two computers to communicate with eachother, either. You can just implement your own thing, and if someone wants to interface with it, they can write their own adapter! Who needs decades of battle tested tooling? This can be a Not Invented Here safe-space. Why not.

I think you're confusing implementing MCP for your own software offering/Saas, which is different and I think you should do it, vs implementing third party MCP servers into a Saas backend, which is what I'm talking about.

Because, to do the latter, the standard design is one hosted MCP server per vendor. If you use more than even 5, that's a lot of servers to maintain in a Saas context.

You think you're being sarcastic, but you don't get the point - implementing 3rd party Saas tools in your Saas backend means one MCP server per service, which can quickly add up, not to mention is bad design. I'm not opposed MCP protocol itself, it's just not needed if you're providing a Saas that talks to many vendors, you don't necessarily need MCP for it.

Also, MCP is relatively new, not "bAtTlE tEstEd"

ah that's a great point. noted.