[flagged]
You are bot!
Are you team MCP or team CLI?
21–26 of 26 posts
Re: Are you team MCP or team CLI?
#22Re: Are you team MCP or team CLI?
#23I think CLI should be the default where supported. i.e. the AI has already been trained on Supabase, Heroku, AWS.
For everything else, MCP.
Re: Are you team MCP or team CLI?
#24Both- depending on the work. CLI for anything local and deterministic: code tools, builds, git, file ops. The agent already knows how to exec commands and parse output, and when something breaks you get stderr and an exit code. MCP for discovery and remote services where the agent needs to figure out what's available.
They solve different problems, but imo MCP has a speed overhead problem that cli tools don’t usually have - so my preference is CLI.
Re: Are you team MCP or team CLI?
#25Peter Steinberger, creator of OpenClaw, is team cli. He has some good arguments in the podcast with Lex Fridman.
Re: Are you team MCP or team CLI?
#26To me it depends on the intended use: - MCP - if you need discoverability. a great example for this is something like context7 - CLI/API + Skill: When you have a defined workflow you want to use. For me a good example of this is using the Linear GraphQL API instead of their MCP I prefer the Linear API because, where I work, we have come up with our way of using the tool so I don't need the entire MCP to do what I nee…
[dead]