M (Model Context Protocol) is all the rage in the AI world and I'm sure most people are either intrigued or absolutely sick of it, but it's kind of a neat tool to play around with for those inclined. There is a slight bit of a tech "know-how" barrier in order to use it, but it's still fairly straight-forward, especially if you already use the Claude desktop app. I created an open-source project that can be found at cswkim/discogs-m-server. The REE has pretty much all the documentation so give that a thorough look. It's still a bit of a work in progress with a decent amount of TODOs, but there is enough functionality to give it a try. I'd like to keep this thread open for any questions people may have, especially for the non-coders out there.
As anyone who has used AI apps like ChatGPT and Claude can attest to, they can be a tad finicky and respond better when the prompts are quite specific. s who know the Discogs API well and understand how to make requests may run into less issues.
stumbled upon your post while trying to get an m server up and running using the python-sdk and discogs python library. And decided to forego the effort since yours is working very nicely indeed!
stumbled upon your post while trying to get an m server up and running using the python-sdk and discogs python library. And decided to forego the effort since yours is working very nicely indeed!
