MCPs are diminishing in value a bit, because AI Agents are getting smarter about using API/CLIs. For example, I use gh cli via Claude instead of their MCP, because I already had cli setup, so no need to use MCP.

MCPs can potentially have great value if they cross multiple sources and combine results. For example at work we use an in-house MCP for log/metrics search across five different (legacy) systems. It finds correlation across events in different system within minutes.

▲

newman314 5 hours ago | parent | next [-]

FWIW, it appears that using the gh cli is much more token efficient than MCP so that's a plus.

https://medium.com/@ravi.madabhushi/mcp-is-up-to-32-more-exp...

▲

sammorrowdrums 4 hours ago | parent [-]

I see benchmarks a lot working on this, and I honestly think there’s too many things to cover in this comment but: - this article doesn’t enable tool search for starters where tokens start at near zero for MCP too - even with the above, talks of the raw token count don’t consider that for very long trajectories the prompt cache amortises much of this cost, and a feature of MCP is you can also customise the tools to a select subset, and that’s powerful - you can add tool confirmations for write/destructive actions trivially - the old training data on CLIs is good but actually for new features the fact MCP advertises them is also a bonus, but that takes longer to see, MCP isn’t that old

There are many more aspects, but even with GitHub MCP, where the agent has a huge amount of pre-training on the CLI, there are still reasons why people use it extensively - you don’t hear it a lot here but suffice to say usage never stopped growing to this day.

I think if CLIs are working for you then good, I also like our cli and did some work on it too, like adding gh skill subcommand.

Do use what works, and measure and improve - but this article is not doing justice to the MCP server IMHO.

▲

throwup238 3 hours ago | parent [-]

> - this article doesn’t enable tool search for starters where tokens start at near zero for MCP too

Is that why I have to constantly remind Claude and ChatGPT that they do have access to a Github plugin that can access my account, instead of trying and failing to use the gh cli?

	▲	gycom 2 hours ago \| parent [-]
		"claude, stop shelling out to grep, your search tool uses ripgrep and it's faster."

▲

kobalsky an hour ago | parent | prev | next [-]

MCP doesn't expose service credentials to the AI.

	▲	kaoD 44 minutes ago \| parent [-]
		I definitely think that's a bridge to gap, but MCP is not the answer. OSes currently lack the tools to do this properly, but I hope they will improve. Agents need more granular sandboxing in all areas.

▲

skerit 5 hours ago | parent | prev [-]

I use MCPs all the time, but just like in your case: they're my own MCP servers.

They do exactly what I want and how I want it. They expose just the information and the features I want the LLM to have. And just like in your case, it combines multiple sources of information into 1 response.