total MCP victory, some quick misc thoughts about why MCP is so much better than CLIs: - indexable tool catalog letting agents scale to unlimited tools - no requirements to be running a full sandbox - consistent auth across all MCPs rather than each CLI inventing its own auth - multi account support for all MCPs unlike CLIs - implementations like code mode let the model know what will be returned allowing for super efficient token usage unlike CLIs the reasons it took this long for MCPs to finally have their moment is mostly due to bad MCP implementations in clients: - you had to restart your whole client to use an mcp (no hot reloading) - agents weren't as familiar with debugging mcps as they were CLIs, so it was a lot easier for people to get set up using them but over the past year, things like codex and claude plugins have all been using MCP under the hood, i.e computer use is an MCP, i believe claude artifacts are an MCP app, just the silent steady adoption there is still an element of MCPs that is 'this MCP could've been an OpenAPI spec' but that'll go away as things like triggers get more adoption at the end of the day, what's important to realize is while yes there are these difference between CLIs / MCPs / etc they're all just different ways of doing tool calling, and you can do some combination of lazy loading, searchable tools, and filtering to build efficient harnesses

I get asked a lot 'how should I build an MCP server?' or 'should i build an MCP or a CLI?', glad to see someone finally doing it right excellent example of what to do and how here by Andre w/ Neon, putting a cleaner layer on top of their openapi spec and making that accessible

I feel like this video is worth a watch for the answer of the question of "what will software engineering after agents be?" So many tiny details and so much love for the craft, with the energy being put into the details, not the implementation

My rough prediction here is there's going to be two types of companies: 1. Companies that are ok with basically being an API - they expose an MCP, skills, embrace your agents 2. Companies that charge a ton for API access, try to get you using their own agents, Companies will gravitate to #2# because being API only is scary / feels very replaceable opening opportunities for #1# companies to replace them because they're more agent native I don't have a good answer for what the moat is for #1# companies but it's how I want to be using software

anyways this is academic slop and the authors should be embarrassed to have published it if you want to try out how MCP is meant to be used, give a try and see just how good it can be - i had to read this slop paper so i get to shill myself now

I read through this paper and it's riddled with errors, partially ai generated, & represents a lack of understanding of the space How do you do an entire research paper on MCP without mentioning lazy loading or codemode? Will share all the problems with it in the thread