even if you try to provide an MCP of your existing product so any AI client can interact with it, I would argue APIs are a better implementation.
Ask HN: Who is using MCP in production?
121–130 of 216 posts
Re: Ask HN: Who is using MCP in production?
#122We use MCP in production.
We built an MCP integration for agentic access to our platform, Proxybase [0]. It lets agents buy and sell bandwidth through SOCKS5 proxies directly from the platform.
The main benefit is simpler integration with agentic harnesses. MCP still accounts for only around 20% of the agents using Proxybase, but it has made the integration process much easier for those users.
Re: Ask HN: Who is using MCP in production?
#123Earlier quoted context omitted.
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...
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?
Re: Ask HN: Who is using MCP in production?
#124Yes, quite a few uses in prod, main use case being abstracting API access for agents. In our case these are mostly in-house MCP servers, purpose built for the given agent. Why MCP instead of CLI or agent accessing API directly? Direct access (Curl/own small function): This requires agent to have full understanding of the API spec. Yes, context can be protected using progressive disclosure, but this essentially means…
We have taken to letting our agents use specific CLIs directly and we narrow down their access control with nono tool sandboxing via a customized Pi agent running headless. We have one agent that can use the aws CLI and nono feeds in a phantom SigV4 credential and then policy limits to just read-only http methods and certain L7 filtering on paths to limit its abilities - this means we can have it monitor and debug de…
How is this better than using MCP?
Re: Ask HN: Who is using MCP in production?
#125Yes, quite a few uses in prod, main use case being abstracting API access for agents. In our case these are mostly in-house MCP servers, purpose built for the given agent. Why MCP instead of CLI or agent accessing API directly? Direct access (Curl/own small function): This requires agent to have full understanding of the API spec. Yes, context can be protected using progressive disclosure, but this essentially means…
I'm really curious how you're dealing with lazy loading. Is the MCP then more like a tool-helper instead of the tools themselves? I was trying to find out if the MCP has some sort of lazy loading feature/primitive in the works, but there seem to be a lot of disagreements about it. Intuitively, lazy loading seems to be somewhere between a CLI and vanilla MCP. In the end, it sounds very similar to tiered/ progressive l…
The lazy loading is a harness concern.
Re: Ask HN: Who is using MCP in production?
#126My company (I'm not part of the team that's responsible for anything AI related) has MCP's for Jira, Confluence, Mattermost fork and a few other integrations.
I have no idea about MCP vs API question but I always assumed that the whole point of MCP was an abstration between the model and the tool\service.
As in model does not have to know about a certain API (not to mention a particular version of it) to work with a service.
Re: Ask HN: Who is using MCP in production?
#127I use MCP for two types of things: ones where I need to give access to the memory of the process like an MCP server to inspect a Qt gui, and ones where I need to give authenticated access to my data to ChatGPT/Claude web/mobile apps. For these uses CLIs would be too cumbersome in use or auth.
For the latter, Cloudflare Tunnels + Zero Trust + Github SSO means securing them is rather easy and with the recent cf cli the agent does all the work. Their native support for base64 encoded images is also helpful to “encourage” the LLM to look at stuff without constant prodding.
Re: Ask HN: Who is using MCP in production?
#128MCP 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 much.
Re: Ask HN: Who is using MCP in production?
#129We offer MCP and then consume it with our in-app assistant to go from a non technical prompt to a series of what is essentially API calls they can automate for themselves for repetitive tasks or things that require a few screens to accomplish can be done from the assistant widget itself, etc.
Re: Ask HN: Who is using MCP in production?
#130I don't use MCPs much for personal use, but I've come to see the benefits of having a standardized mechanism for distributing tools across non-dev teams, especially when they're using a hodgepodge of agents.
I'm also excited about the upcoming SEP-2640 extension to MCP, which will be allow skills to be delivered via MCP. While the skill format has been standardized, skill distribution hasn't. I know there are tools like Vercel skills CLI, but that's not a good option for non-devs.