I quite liked this article, actually, and I'm quite an MCP stan. These all seem like legitimate problems that the burgeoning ecosystem needs to figure out. Some of them will be logically solved inside the MCP spec, but I also think some won't.
I mean, obviously you want to run the local CI in some isolated way. But it's not such a bad idea for many projects.
At PyTorch, we have the reverse problem, it's basically infeasible to run the CI locally, you really do need the cloud setup to cover all of the operating system / hardware configurations, and the parallelization in cloud also saves you loads of time.
One thing I'll say, is that if I was going to make people pay API costs (like cline/claude code) I probably wouldn't actually make an MCP. The MCP box is pretty limiting, and I'm only willing to pay the cost because that's how I get onto flat pricing structure.
I definitely agree that for current models, the problem is finding where the LLM has comparative advantage. Usually it's something like (1) something boring, (2) something where you don't have any of the low level syntax or domain knowledge, or (3) you are on manager schedule and you need to delegate actual coding.
One problem with keeping the changes separate is the LLM usually wants to test the code with the incremental new changes. So you need a working tree that has all the new changes. But then... why not use the real one?
So I have liked the Claude Pro style rate limiting over credits that refresh monthly but mostly because I only get snatches of 1-2 hours while I am on baby leave so I never actually get rate limited. As for learnings, I put a lot of them in my AI Blindspots blog, cuz I did most of codemcp's dev with LLMs
The thing is that, as many junior engineers can attest, randomly blundering around can still give you something useful! So you definitely can get value out of AI coding with the current generation of models.
I have used Cursor and my own MCP codemcp. Cursor has a lot of nice QoL that you can't get from an MCP package; the TAB is really good for traditional coding. Haven't used copilot so I don't have a comparison there. Definitely use agent mode.
Cline has famously huge API token costs as it is profligate with context. Because codemcp plugs into Claude Desktop you only pay for your Claude Pro sub, similar to Cursor's pricing model
In my experience, the model is king, and codemcp will operate fairly similarly to Cursor with the same failure modes as Cursor due to Sonnet 3.7. One thing that I like about codemcp is I can customize aspects of the interaction as I discover new things I want to do :)
Yeah, Sonnet 3.5/3.7 are doing heavy lifting. Maybe the SOTA Gemini models would do better, I haven't tried them. Generating correct patches is a funny minigame that isn't really solved, despite how easy it is to RL on.
In fact, the test framework I was using at the time (jest) did in fact support this. But the person who had originally written the tests hadn't had the foresight to use snapshot tests for this failing test!
I'm surprised you managed to get Desktop running on Linux lol. You don't need the filesystem/git MCPs alongside codemcp; in fact, it's better not to have them so that Claude consistently uses' codemcp's equivalents to do edits. I'm not sure why codemcp's built-in git support did not work; you can probably find out more by looking in .codemcp/codemcp.log.
If you need to start a new chat, it works just fine. Tell Claude what's happened so far and what you want it to do. You can also ask Claude to summarize the old conversation, that's how /compact in claude code works too.
Hi Hacker News! One of the things about this blog that has gotten a bit unwieldy as I've added more entries is that it's a sort of undifferentiated pile of posts. I want some sort of organization system but I haven't found one that's good. Very open to suggestions!