Ask HN: Who is using MCP in production? • Hacker News Board

Re: Ask HN: Who is using MCP in production?

#141

Post by gycom » Fri, Sep 04, 2026, 1:16 PM UTC

throwup238 wrote: post #123

sammorrowdrums wrote: post #115

Earlier quoted context omitted.

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…

> - 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?

"claude, stop shelling out to grep, your search tool uses ripgrep and it's faster."

Re: Ask HN: Who is using MCP in production?

#142

Post by edgyquant » Fri, Sep 04, 2026, 1:23 PM UTC

kqr wrote: post #82

SegmentTree wrote: post #71

We use MCP when security and tight capability boundaries are important. For example, even GitHub’s fine-grained tokens aren’t always fine-grained enough for our use cases. In those situations, it’s straightforward to build a small MCP server that exposes exactly the operations we want an agent to have access to. That gives us a much smaller and more explicit attack surface, without having to manually audit every poss…

I get this use-case, but what makes an MCP server better than a custom CLI tool that exposes those same operations? That's how I've solved similar things in the past.

Mcp just wraps the existing calls with a description of when to use them. Why would you write a cli for something like this? And clis generally have a help call but that doesn’t say when to use a tool just what it does

Re: Ask HN: Who is using MCP in production?

#143

Post by kobalsky » Fri, Sep 04, 2026, 1:25 PM UTC

5ersi wrote: post #97

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 cor…

MCP doesn't expose service credentials to the AI.

Re: Ask HN: Who is using MCP in production?

#144

Post by rgbrgb » Fri, Sep 04, 2026, 1:39 PM UTC

at Hedgy we built an MCP to give our agents read-only access to cross-system data + context about what it means [0]. daily it helps me debug customer flows and think through features and priority.

the advantage of MCP is that the tool description names what data it has so the agents know to just use it if they want that kind of data. as new data is added, everyone’s tool description updates. with a REST api or cli I suppose we could update a checked in AGENTS.md to ship it to engineers but idk how id get that to colleagues using the it from their claude.ai or co-work.

[0]: setoku.com

Re: Ask HN: Who is using MCP in production?

#145

Post by owaiswiz » Fri, Sep 04, 2026, 1:40 PM UTC

We do have an MCP but all it does is wraps our OpenAPI endpoints using a bunch of tools (not exposing the 100(0?)s of endpoints as tools), but just list_resources, list_endpoints, describe_endpoint, describe_ref, execute.

The primary reason we have this is because its easier for non-tech people to connect it to their AI Claude/ChatGPT/etc. than it is to have them generate an API key and give it the base url and the openapi spec/etc.

The MCP also allows us to add expose a couple of recipe/skill tools (list_skills/read_skill) which describe common workflows on how to use to do things that might be unclear.

Re: Ask HN: Who is using MCP in production?

#146

Post by ssenssei » Fri, Sep 04, 2026, 1:42 PM UTC

I just HAD to use it today, I avoided them as much as I could. We have a figma design that's not really enterprise level with different components and not really coherent in some ways, and the management want the web pages to be the exact same as the figma designs.

Knowing the hell that awaits me in trying to be pixel perfect between about 40 pages, I set up the Figma MCP with my codex, and low and behold... it actually did what I needed, so that's one thing I'm grateful for.

For reference, feeding screenshots to the AI didn't do that well of a job at first.

Re: Ask HN: Who is using MCP in production?

#147

Post by dawdler-purge » Fri, Sep 04, 2026, 1:45 PM UTC

I use MCP to create and manage forms on Tally (tally.so). It works very well.

Re: Ask HN: Who is using MCP in production?

#148

Post by allknowingfrog » Fri, Sep 04, 2026, 1:59 PM UTC

edgyquant wrote: post #137

deadbabe wrote: post #113

Earlier quoted context omitted.

Do you not expose a standard REST api?

MCP is not just a rest api its a layer on top

A layer than honestly doesn't do much, as I understand it. What does MCP as a protocol actually solve? Is it more than a bandwagon?

Re: Ask HN: Who is using MCP in production?

#149

Post by amclennon » Fri, Sep 04, 2026, 2:01 PM UTC

edgyquant wrote: post #138

cgarvis wrote: post #128

MCP is for when your end user (the one driving an LLM Agent) is non technical. Most non technical people are not going to install a CLI on their computer. Most are not going to be driving the LLM agent via a terminal. It also very helpful when you need auth. MCP OAuth with CIMD makes it easy instead of cumbersome process of generating API Keys. If you are technical and already using CLIs, then MCP doesn't give you mu…

Even with a cli it doesn’t have a nice list of all commands and a nice description of when to call such a tool

I often find that a lot of models will call the `--help` flag to figure out the commands and arguments nowadays. If I use a cli repeatedly, I'll generally ask it to create a skill

Re: Ask HN: Who is using MCP in production?

#150

Post by kaoD » Fri, Sep 04, 2026, 2:07 PM UTC

kobalsky wrote: post #143

5ersi wrote: post #97

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 cor…

MCP doesn't expose service credentials to the AI.

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.