unknown

Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck.

So we hit the streets of SF to see if the city agreed.

We posed a simple question: MCP or CLI?

- Basically everyone under the age of 35 said CLI
- One person said MCP was as bloated as Java 
- & unsurprisingly, numerous people told us to touch grass

Final score- MCP: 3 vs CLI: 17

SF has spoken, and @composio listened.

Our universal CLI is now live!

Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀

Link to try our CLI in the next thread ⬇️

<p>Okay, @gdb is team CLI all the way. @garrytan thinks MCPs suck.

So we hit the streets of SF to see if the city agreed.

We posed a simple question: MCP or CLI?

- Basically everyone under the age of 35 said CLI
- One person said MCP was as bloated as Java 
- &amp; unsurprisingly, numerous people told us to touch grass

Final score- MCP: 3 vs CLI: 17

SF has spoken, and @composio listened.

Our universal CLI is now live!

Drop your best CLI vs MCP hot take in the comments and we'll send the best ones some very sick gear 👀

Link to try our CLI in the next thread ⬇️</p>

Robert Youssef

A provocative claim that in an informal SF developer survey, 17 out of 20 developers chose CLI over MCP, with zero developers under 35 picking MCP. The post frames MCP as a legacy-adjacent choice and CLI as the dominant preference among developers actively shipping in 2026.

17 chose cli. 3 chose mcp.

@composio went to SF and asked real devs. not researchers. not maintainers. people shipping things in 2026.

zero people under 35 picked mcp.

the 3 who did will be fine. they're used to supporting legacy systems.

<p>17 chose cli. 3 chose mcp.

@composio went to SF and asked real devs. not researchers. not maintainers. people shipping things in 2026.

zero people under 35 picked mcp.

the 3 who did will be fine. they're used to supporting legacy systems.</p>