News for hackers. Stuff that matters.
Re:Ask HN: Who is using MCP in production? by 5ersi on Friday September 04, 2026 @05:39AM (#49562408)
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.

Re:Ask HN: Who is using MCP in production? by newman314 on Friday September 04, 2026 @06:19AM (#49562684)
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...

Re:Ask HN: Who is using MCP in production? by sammorrowdrums on Friday September 04, 2026 @06:52AM (#49562869)
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.

Re:Ask HN: Who is using MCP in production? by throwup238 on Friday September 04, 2026 @07:35AM (#49563205)
> - 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?

Re:Ask HN: Who is using MCP in production? by gycom on Friday September 04, 2026 @09:16AM (#49564202)
"claude, stop shelling out to grep, your search tool uses ripgrep and it's faster."
Re:Ask HN: Who is using MCP in production? by dleech on Friday September 04, 2026 @12:13PM (#49566637)
0verload.net ... I am the Author if the tool. I cloned grep and hopped it up a with a bunch of globs and stuff only a bot can really use. You can version control directorys ...its not meant to replace git.. I wronte it for my self because I was tired of wishing it hadnt been a week since i checked into github. I have not have regression at all since I started using it ..its a godsend.it increases the effective context size by a huge ammount..if you learn to use it correctly you can have hundreds of megs of context without a problem and share it between agents. Additionally theres an edit monitor that throws every file and the diff for all the things the bots edit and you cvan scroll thru the sessions edits holding alt down and page thru the days code. ITs meant to be a pair programming tool to use with claude code. I have full mcp support but I also have a more powerful scripting language.mcp support is just part of the scripting language..so is rest..the whole thing is bot centric..I have guis for itm all but you can just tell the bots to o stuff ..I made the bot interfaces for everything and then the gui. Oh..it caches all the memory contexts and all the verson controlled filex in ram so grepping stuff in the source controlled folder is considerably faster..anwhere from hundreds to I have seen 6000+ times faster grep results not thru any sort of black magic..its just what happens when a custom written grep has a in ram memory or an in ram version controlled store to look thru..Its not magic ..rams alot faster..yes ..6000 sounds like I'm throwing numbers out that cant happen ..ok ...try it
Re:Ask HN: Who is using MCP in production? by 0x457 on Friday September 04, 2026 @04:37PM (#49569924)
"claude: my harness tells me to use python's pathlib"
Re:Ask HN: Who is using MCP in production? by sammorrowdrums on Friday September 04, 2026 @01:22PM (#49567493)
Most likely, personally I have thoughts on tool search, I don’t believe it’s the final stop on the road to MCP progressive discovery, but it does have its uses. Especially for very large tool catalogues.

Expect more on this. We are looking at the problem.

Re:Ask HN: Who is using MCP in production? by skerit on Friday September 04, 2026 @06:18AM (#49562670)
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.

Re:Ask HN: Who is using MCP in production? by kobalsky on Friday September 04, 2026 @09:25AM (#49564301)
MCP doesn't expose service credentials to the AI.
Re:Ask HN: Who is using MCP in production? by kaoD on Friday September 04, 2026 @10:07AM (#49564866)
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.
Re:Ask HN: Who is using MCP in production? by manveerc on Friday September 04, 2026 @01:04PM (#49567254)
This is not true by default. There are plenty of poorly implemented MCP servers which do that. The MCP spec supports Oauth and intends to avoid that but it is not enforced.
Re:Ask HN: Who is using MCP in production? by tirpen on Friday September 04, 2026 @12:37PM (#49566936)
The main benefit of MCP today over just giving an agent a CLI is of course that you can be a lot more certain about what the agent can or can't do.

Yes, an agent with CLI access and access to making HTTPS calls is a lot more efficient for most tasks, but also a lot more unpredictable and with much higher blast radius if it starts misbehaving compared to one that only have access to exactly the tools and data sources you want it to use.

Re:Ask HN: Who is using MCP in production? by dmazzoni on Friday September 04, 2026 @05:38PM (#49570528)
In practice that’s a lot of the value MCPs are providing.

Technically it’d work just as well to have a thin API wrapper or cli tool the agent is allowed to access.

Re:Ask HN: Who is using MCP in production? by dominotw on Friday September 04, 2026 @01:21PM (#49567481)
gh cli prbly has a lot of training data so maybe not a fair comparison
Re:Ask HN: Who is using MCP in production? by nojito on Friday September 04, 2026 @01:40PM (#49567749)
No it's because any model can do gh --help

cli tools are a natural fit for llms.

Re:Ask HN: Who is using MCP in production? by dominotw on Friday September 04, 2026 @01:46PM (#49567828)
actually run it now and see it wont do the help command you are talking about
Re:Ask HN: Who is using MCP in production? by EyeEmOe on Sunday September 06, 2026 @02:47PM (#49589566)
Agree with this.

MCP and RAG feel like the usual pattern of running a daemon 24/7 that balloons infrastructure spend. So uncivilized.

Any given REST API is a small model. A frontier or local model and modern harness can parse the already existing documentation for that REST API and invoke or generate a tool to use it.

Re:Ask HN: Who is using MCP in production? by apexchaos on Monday September 07, 2026 @07:36AM (#49597091)
there is a number of importance that MCP can provide you outside using API/CLIs. when integrating with external services and you want a deterministic layer for your agent that can scale independently as your agentic layer in complex system while providing functionality like prompts and static read-only resources that can in turn be used for context injection and optimization. you might want to use MCP when it is this but for local services with alot of dependency or you want to write alot of wiring code, you can settle for API/CLIs