I’ve been following MCP since it first came out. It got a lot of attention early on, but I haven’t come across many people using it in production. I may simply have missed them.

If you’re using MCP in production, what are you using it for? What advantages have you found over a normal API or direct tool integration or just CLI?

[delayed]

I built an MCP server for my voice assistant. By default, Home Assistant offers a few tools to the models, but I felt like it was missing some, so I built it.

It has tools to get real jokes, do math, unit conversion, get stock information, search the web with Kagi, and other things I consider to be essential in a voice assistant. It even got approved by my wife.

At work I use our MCP server to debug and troubleshoot issues with our code too. Just yesterday I used it to figure out why a tag wasn’t showing up in traces; using the MCP server, the LLM was able to see that the tag was present in parent traces, but was lost along the way, and figured out why.

Could I find that without the MCP server? Yes, but I’d take me hours of going through lengthy traces, while the MCP and LLM found the issue in minutes.

We use MCP in production since March 26 for user-facing endurance sports analytics and planning that integrates directly with the MCP host, in this case the chat interfaces of ChatGPT, Claude, Grok, Perplexity.ai, Mistral, you name it. All of those let users add either custom MCP servers, which users can do with a simple explanation. To connect Claude for example: https://www.tredict.com/faq/connect-claude-web-with-tredict/ This way users can use Claude to create and push workouts with their Garmin devices based on a prior analysis. We also have a ChatGPT App, which uses MCP in the background: https://chatgpt.com/plugins/plugin_asdk_app_69aef5b699a08191...

The point here is, MCP is the backbone behind the product and enables regular users to do things without knowing anything about it.

The whole "is MCP useless?" discussion is totally pointless from a regular consumer-user perspective, they even do not know what MCP is sometimes. The Tredict ChatGPT App connects with one click and a simple oauth flow. That's it.

I 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.

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.

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 much.

My 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.

MCP Apps are the only way to build a connector that's actually usable from inside the Claude and ChatGPT apps. They return chunks of UI alongside the tool result, so a CLI simply can't provide the same functionality.

And you can't expect an average user to install a CLI on their machine just to search for flights or do shopping for example.

I work at Alpic, where we build Skybridge, a framework for developing MCP Apps. Our users have apps published on the ChatGPT and Claude stores, and they've seen traffic quietly growing over the last few months. Traffic isn't massive yet, but it costs little to stake out ground on a new channel and be ready if it takes off.

We use MCP in production for our customer facing voice agents. Our custom MCP server defines tools and resources that the voice agents need access to to interact with our customers. (E.g. scheduling appointments, checking order status, etc).

Now we can point any voice agent platform we choose -- eleven labs, vapi, pipecat, whatever -- at our custom MCP server and it instantly has an understanding of the tools available, their inputs, and how to use them.

Compared to the alternatives everyone on HN champions, like clis and APIs, this is a no brainer. I'm honestly not even sure what the realistic alternative would even be.

Am I supposed to package and distribute a cli to ElevenLabs and ask them to use it? Give them a full API spec to implement for me?

I give them an endpoint and credentials and their platform instantly knows how to talk to mine. No one at ElevenLabs knows or cares about our implementation details.

HN has trouble seeing past the "developer in a terminal coding with Claude Code" use case for using AI. Real production agents have use cases that are very different!

When you don't own every piece of an integration with another system, there needs to be a well defined standard. That's what MCP provides.

Yes, 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 agent needing to understand the API again and again, before every use in that context. Also, a typical API spec may or may not be agent-friendly. If there are nuances when calling an endpoint, where do we put these? Into OAS description? Works, but clunky.

CLI: It works beautifully, especially when a 3rd party CLI already exists for a complex backend. Assumes a well documented, agent friendly CLI, most CLIs are designed for human or CI/CD consumption. Talking about MCP taking up too much context, think about agent starting with my_cli --help, and going down through the switches and parameters one at a time to figure out how the CLI should be called. Less of a problem when calling a well know CLI (e.g. aws), but anything more niche (or custom) requires multiple turns to compose the final CLI command.

MCP: Has its issues, but offers an agent-native solution. Everything agent needs to know about a tool becomes available at once. In an enterprise environment MCPs can be served through an MCP Gateway, providing governance and permission management, this is quite contrast against running a CLI that requires agent to have execute permissions in its shell.

I must mention that we also utilise lazy-loading of MCPs. In use cases where 10s of tools needs to be loaded, only the most common ones are pre-loaded, then agent kernel connects the others as an when needed, and release them after a timeout (in case of long running sessions). This keeps the context lean.

I OCR'd my Chinese textbooks and made a stateless MCP that allows me to ground my Chinese language studies according to the textbook only. With this I can start a quiz, understand differences between words that have similar meanings knowing no extra grammar is fed when reviewing. I specifically use it with glm 5.3 as it is the most language specific LLM that understands nuances.

Here's the repository: https://github.com/iodize6399/xuexi-keben

And here's the server itself: https://keben.555420.xyz

My context is realtime visual effect creation, but I’ve used MCP extensively in my (native) custom harness as a way to drive in—app UI updates and of course bidirectional state queries, including framebuffer capture for closed loop verification.

I feel like CLI would probably work too but then I’d end up implementing something similar. That being said, I’ve been bitten by the usual suspects: too many tools will cause context windows to grow quickly and some agents will sometimes skim through a subset of the tool list without querying the entire thing, causing incorrect behavior.

If you have tokens to burn I invite you to check out the source code see how extensively it’s being used: https://github.com/sxp-studio/subjective-zero

(video to see the MCP in action, it’s a bit long so feel free to skip: https://www.youtube.com/watch?v=DcI1tsPJ8eM)

Another kind of cool use of MCP that I’ve encountered is actually from… the French government! They do it for their open data initiative: https://github.com/datagouv/datagouv-mcp

For what I am using it for, I recently wrote a little web app called Afterfeed [0] that lets you view backups from social media websites as a single unified timeline.

To put this into perspective, I was a voracious social media user for decades. For me, this is 25 years of data, close to 100,000 posts, spanning everything from LiveJournal in 2001 to Mastodon in 2026. But when put together, it is a timeline of my life.

As kind of a last minute idea, I added an MCP server because why not? Once I wired an LLM up to it, I could ask introspective questions and find new ways of looking at myself and my own history. Simple things like "what was I doing 10 years ago around this time?" to more complex things like researching past thought patterns.

[0] https://github.com/rebeccathedev/afterfeed/

My employer Notion offers an MCP that’s mentioned in a few posts here.

Notion’s monorepo has 16+ MCP configs with many in opt-in plugins developers choose to activate.

Very useful; i particularly like sending an agent to debug an alert across slack/honeycomb/incident.io/materialize db

MCP usage is at an all-time peak - 17M daily (!) downloads of the official SDKs.

We're using MCP for virtually all our SaaS and infra providers (CRM, ATS, banking and accounting, Notion, Linear, all dev tools and hosting platforms) it's become a hard requirement in our buy bechmark. No MCP = NOGO

The advantages are:

- baked-in auth: no need to configure anything, it just works with our employees accounts

- one click install with Codex Plugins and Claude Connectors

I recently started using it as a way to make my own custom software available to regular ChatGPT and Claude, both of which support MCP if you dig around deep enough. Here's my TIL: https://til.simonwillison.net/llms/mcp-in-claude-and-chatgpt

I use feedbackjar mcp. It's a feedback tool which also collects metadata like device, os, browser console etc. So my coding agent gets all the context of the feature request or bug report. https://feedbackjar.com

I hooked up claude code to Jira and Figma. This is more a condemnation of Jira than anything, but being able to interact with it in natural language in the terminal is a huge relief. Sadly, it's still limited in some ways. If it's available, it makes things a tiny bit easier than interfacing directly via api, so it's a nice to have.

I 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.

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 possible GitHub CLI invocation the agent might make.

We 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.

At Adidas we use MCP in production, both flavors stdio and remote. Remote is more for secure autonomous agents or agents workflows and stdio is more intended for local development. So far we are good with this still don't see the point of A2A except some really specific cases, if you have the tools and a smart model do you need really split with different agents?

I assume the target audience for the question is developers. That will generate many responses along the lines of ”just use a CLI”.

The current, main driver I see for MCP servers are non-technical people who want to securely connect data sources to their AI application.

For us it's pretty much a standard request from our clients now: that they are able to use their chatbot to interact with the ERP systems.

We (HappySupport [1], help center with lots of automation) recently added an MCP server - this was highly requested. Our users are using it to reorganize their help center, answer questions (internally) and to create/edit/move/publish/unpublish or delete articles.

It was also pretty handy for importing existing documentation from obscure providers without having to build an integration for each of them.

We also added WebMCP [2] for agents to consume our public documentation/help center, but we haven't seen it used yet.

An API would work for all of these cases too, but since customers are using it in their AI tools anyway, MCP is just simpler for them.

[1] https://www.happysupport.ai/en [2] https://developer.chrome.com/docs/ai/webmcp

In many cases, you can partition data at rest (eg parquet) on the user access key, then load it once into an agent container at runtime. In this way, one authentication pass provides access to all data in a sandbox, versus repeatedly authenticating against MCP calls. It also just reduces the connective tissue between the harness and the data. There are obviously drawbacks in that you aren’t leveraging real time APIs, but it works well for most business use cases.

I do, was using Grafana MCP to a local Grafana instance for QA-testing my web server.

Running a bunch alongside APIs for suite of internal services where domain experts are using agents to setup environments for their work. Getting them to update their LLMs to a new SDK version every time we iterate API capabilities is all the headache you'd imagine. The MCP avoids inconsistent user reports of capabilities.

The specifics, now user can ask, "Provision 200Gi PostgreSQL 18 with PostGIS 3.6 and then copy over our most recent Texas set of layers."

Behind the scene Talos, k8s, NiFi, and bunch of things go to work. Big productivity boost vs. the users needing to login to bunch of provisioning web interfaces which is the other method we publish that avoids version drift issues.

I use it for fully auditable agentic compliance work - many of my customers already used MCPs for their compliance work, and recent changes made that fully auditable. I have to admit that it's much easier to use and work on compliance this way than using the agent built into the app.

https://auditbadger.com/auditable-agentic-compliance/

I built a small MCP service tool to my own learning; it retrieves study materials and course content, enabling me to learn through voice-based interactive conversations with ChatGPT. logs my learning data, which I can then retrieve and analyze to assess my overall progress.

We (Prostack, UK managed hosting) launched an MCP server for our control panel- https://mcp.prostack.uk - to allow users to interact with Claude/Cursor etc, for debugging & deployment.

"Why is my site showing an error", "Deploy this project" etc are the key flows, and users have been building on top of them. It's a nice link between dev & prod, and a great debugging assistant. It's been very well received so far.

Implementation was pretty straightforward (tools mapped to our API) with appropriate guardrails for destructive actions.

We (Synqly) have a production MCP server which several of our customers use in their production services. The functionality ranges from mundane management capabilities such as walking through how to add an integration in natural language (e.g. support bot) to more than exciting use cases such as making complex queries across a number of tools to create aggregate reports.

It's a very popular part of our platform.

Reporting is what we use MCP for.

We do social media community management ( https://trollwall.ai/mcp ) and our customers want to know what their followers are talking about - topics, sentiment, why are people angry, showing actual example comments, comparing to last month.. Having a conversation about this is much better UX than having dashboard or static report (.. your Claude can at the end even generate PDF report on what you talked about).

We tried to build different analytics screens for this and we always found out that different types of customers what their own angle. MCP, together with knowledge/memory of their own ChatGPT/Claude, allows them to super customize it for what they want and need.

I (SiteSpeakAI) use MCP in production in 2 ways, to analyze usage and make improvements to the app itself to hopefully improve the customer experience, and then also as a feature for each customer so they can interact with their own cx install and monitor / improve prompts etc. Been really useful, but important to note most customers are at least a bit tech savvy, so MCP makes sense for them.

Don't think it would be that useful for non-tech users.

I'm using in production for one of my physical products. The product is a set of 50 printed cards for facilitation. The MCP server can be used by the facilitator to plan their workshop. The reason behind providing MCP is simple: my end-users do not need traditional API, they need something that they can install in their Claude Desktop app and work with the proprietary data of the product. My product's data lives at edge in Cloudflare Workers. (Of course, a determined user can scrap the data if they want, but that's fine.)

Other uses of other people's production MCP I'm using is Dodo Payments' MCP server. It has helped me a ton for looking up their documentation etc. 10xed my OpenCode agent's speed in building payment integration. This was the first serious usage and benefit I experienced of MCP servers.

Reference: My production MCP server: https://www.npmjs.com/package/@sisyphus-consulting/wuwei-mcp

As a user, I use a couple of them with Claude: dash0 + linear + readonly access to a prod db, I can now understand and debug our user's issues in minutes with all the forensic automated.

In our product, we found it hard to onboard people on our platform because even though the data was rich, our features were subpar and in development. I've opened the MCP API based on our GraphQL API (like 100 lines of code and config, piece of cake), and we got heavy usage day 1. The adoption went from convincing them to use the platform, to them flooding us with new feautres and data requests.

I've ramped up my MCP game this year, I started with Linear and Notion and I recently launched an internal MCP for internal data that is being used by my colleagues too for reporting and preparing for meetings with customers (we do upsells for hotels www.upsellguru.com ). It seems like that some of the most tech savvy customers are looking forward to use it too and we may open to them too.

In general the advantage of MCP would be the possibility for a fine grained control over the tools the agent is allowed to use. But unfortunately there is a myriad of nightmarish awful mcp servers around which are worse than direct API access or even a cli integration.

I wont advertise any commercial mcp I use but to give an example for a well designed and useful mcp server I could name the nixos mcp. Its useful because it bundles all the nix resources to one endpoint which is more efficient than web search and gives you better control over the sources.

https://github.com/utensils/mcp-nixos

Another one would be this filesystem mcp which is in my opinion to prefer over direct cli access. Of course this depends also on your general sandbox strategy but if you just use a generic docker image there are still many potentially dangerous binaries available and such an mcp can restrict the models capabilities.

https://github.com/modelcontextprotocol/servers/tree/main/sr...

And of course there are many service provider offering their mcp with its own llm / agent behind e.g. most web search provider. In this case you most likely already use an mcp without noticing it.

I recently created a planning applications scraper for every council/local planning authority in the UK, very much with Claude's help. As you can no doubt imagine, it's the type of task where the mechanics are far less important than everything surrounding them.

Getting things like this to work well, for me, often boils down to finding out the things I don't know that I don't know in as little time as possible. I worked with Claude to create a basic debugging front-end as part of that - for my own use, inspecting the data, looking for patterns - when, largely on a whim, I asked Claude to create an MCP interface on top: last run status, what's looking good, whats not, where are the coverage gaps in the individual data points.

And I added the MVP to Claude and would check in regularly to ask how things were going.

And then - I'd ask for some nuance about why something doesn't look quite right. Or what happened to councils in general last night? And - out of nowhere, not being prompted or asked - Claude would query the MCP alongside looking at the code. Immediate production-grade insight while I'm debugging from the comfort of my chair.

And I thought "Oh."

And "this is really quite good," because the key detail is, I think, if an MCP is good and works well, and relevant to what you're doing every day at that point in time, it's yet another addition to your toolbox.

And that got me thinking about how I can do the same for my 9-5 users.

In my previous company we used MCP for voice agents. It was easy to use open-source mcps, since we did all the oauth and account management on our side. This also makes it easy for customers to bring their internal tools in a standardized format.

I’ve deployed mcp to prod on numerous internal apps where ai-integration has been first party requirement. Obviously, agents can use an existing api, however maximum capability requires it to be well designed and documented. As many of you may have experienced, that is not something that can be assumed and improvements may be “impossible” or at least out of current scope.

That’s where mcp (and recently webmcp) have their benefits. By design, the protocols provide predictable structure that allows agents to discover and use the tools you provide.

I’ve had success using mcp variously as an agent friendly wrapper to an existing api and as a greenfield product designed for agentic workflows. Agentic workflows can string together multiple api endpoints together into a single tool call and or use their own dedicated backends.

To share my learnings, I’ve released a free tool at https://anc.dev . While It’s still very much a work in progress, I’d love dialog and constructive feedback.

Advantages vs skills: connecting to enterprise systems via OAuth.

Yeah you could call CLI tools that support OAuth, but then you have two sets tools (CLI plus a skills file) to manage manually instead of a hosted MCP server.

When writing agentic apps (apps which embed an agent for semantic work), exposing the same tools which are injected into the agents as an MCP allows for practically the same functionality to be debugged and run in a normal agentic harness.

Good for both development and cost reduction, as the agentic harnesses often allow for much greater amount of token usage per subscription, as opposed to API key which always is per volume.

Chatbot+MCP, agentic workflow+harness seems to be the divide in my workplace: Business people want a chat UI, they get MCP. Developers want to automate things, they plug in their dotfiles and other scripts. Not sure if it reflects the larger population.

Custom connector to paperless for processing fetching, reason... Off any physical contract or letter received by the company. Google drive for everything digital. Paperless for more legal things.

I don't know if it counts as production, but I use it for my task tracking, as well as a web GUI. When talking to Claude and working on a plan for a feature, I tell it to cut the tasks into small tickets and write it to my selfmade Ticketboard.

My phone's AI assistant can talk to it too, so if I remember a task mid walk out in the sun, I can just talk to it and it can write it down.

We have it, a fresh tool that landed recently in prod. Makes it easier to communicate with the app resources. And it's a standardised way for agents to talk to a remote resource, easier for them to understand what is available and how to use it.

Read more about mcp tools/resources/prompts.

We use it for access to gitlab, ado, github, datadog, rancher. I think the rancher one is the worst. We develop custom MCP servers for our internal stuff for agents to use, and it all gets accessed thru agentgateway.

I don’t really like having to use MCP but we don’t have a good solution for authorizing individual calls outbound from a sandbox without choosing to just not care about the sandbox.

Our company has an MCP which hooks into a bunch of metrics/analytics that we've been using to do RCA on a whole slew of issues.

We use MCP in our monitoring systems.

A claude routine runs without access to internet except for Slack (API) and Sentry (MCP).

It reads the Sentry MCP, compare the errors to the app source code and post a daily digest to Slack.

The reports are very accurate.

I used one for an AI tool that allows people to report bugs/feature request directly.

It searches to make sure it isn't a duplicate, writes up the ticket, then submits it.

Because it's a production tool, we want the cheapest possible one without it being too inaccurate. If you used a API etc, you'd end up building what's effectively a MCP-like adapter on top of it anyway so it could communicate in natural language instead of dealing with JSON and such.

Linear's MCP is also very clean and well designed, probably one of their core advantages over, say, Jira. I wouldn't know what the API looks like because the MCP works great.

We use mcp as a "gateway" for a customer facing cloud agent. It basically is just a tool registry and could have been built using open-api... but MCP is arguably more robust/aligned for context management and the agent frameworks and observability tools support it first class.

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.

well it is in production but very low usage mapkin.eu and jotkin.eu mainly tools i use myself to send stuff to clients basically persist chat via mcp.

I work with corporate customers, and it has become (literally) the new API management layer, to isolate and audit connections between systems and prevent people from developing random API clients.

Having a hard time understanding what MCP is really for. Even for my small local models, if MCP is not available, they seem to do just fine connecting to anything I need with an API and falling back to using a browser.

My Company developed a MCP ti control our product we ship to Customers. So we use it inhouse for testing. It was so convenient that multiple Software developer adopted the mcp tosetup there test environents

Caudena released some of its enterprise capabilities within MCP last year, and made them available to the consumer market this year at https://mcp.caudexcatena.com/.

We have received very good feedback from clients across the enterprise and consumer segments, they really like it.

I am being working on a new ui framework and will deliver a mcp, a lsp and a skill to help create new apps, because as it is new, it is not in any data used for training any llm.

I work on an F100's internal, vendor/model-independent LLM chat app whose agent runs in your browser, so CLI isn't an option, direct API is out as the agent deliberately doesn't have any tools for hitting arbitrary URLs and it can't access the network via its iframe-sandboxed code execution tool, so we use MCP in the harness to let it do third-party things, with e.g. Atlassian and GitHub MCP servers pre-configured and support for BYO MCP if there are compatible third-party servers you want to use, or are running your own locally to provide tools to let it do things on your machine (it can already be given R/W access to your local filesystem via showDirectoryPicker()).

The biggest issues are usually that a third-party MCP server you're trying to use either has misconfigured CORS so the browser can't hit it, has a bespoke OAuth setup which doesn't work with @modelcontextprotocol/client, or they don't support Dynamic Client Registration (DCR) so you can't just point at it and use it. It's nice when none of these apply and it Just Works, the user can auth easily with the third-party and refresh tokens automatically handled in the background by the client.

That's the advantage, really - you didn't have to define the tools yourself, auth is handled for you, and the agent doesn't need to (and can't) access credentials or tokens as it knows nothing about MCP.

Linear MCP, custom made Node-RED MCP and a custom made ERP vendor MCP.

All prove great value.

I use fff [1] For the performance improvements when reading files. I prefer in most scenarios to use skills.

(1) https://github.com/dmtrKovalenko/fff

Internally we have MCPs for many many tools, I would expect if anyone builds a product or new feature today it has an MCP or skill

Building an agent runtime at cadenya.com and MCP servers have been the hardest part to create adapters for. For a two year old spec, there's far too many permutations.

I find clis or calling apis directly to be waaay cheaper and faster. The only mcp i use at this point is the jira mcp only because i set it up a while ago and it's been there for a long time now

MCP is still the main way I use Cursor with enterprise systems like Glean, Jira, and Port. Other than that, everything, especially you GitHub, is moved to CLIs (+skills as needed)

We 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.

[0]: https://proxybase.xyz

many things once needed a MCP server now could be easily done via using CLI by agent

We use for jira, confluence, excel. Attlassian projects require Rovio and this is additional payments. So we wrote our mcp to connect and work with them

I use MCP for Stackography, a tool I built that visualises my estate (hosts, apps, databases, tunnels, proxies etc), showing a force-directed graph, which includes live health, and a flexible search tool. It's very good for answering questions like "what stuff am I running under Docker", or "show me everything that makes up app X". Also shows the history of changes, summarised by LLM.

MCP is useful because it has instructions to Claude (or the agent of your choice) that tell it how and when to manage the graph. Integrating with Stackography is a one-line operation:

    claude mcp add --transport http stackography https://app.stackography.com/mcp --header "Authorization: Bearer stk_...

invite link: https://stackography.com/invite/8J22NXZSFT

I use almost no MCPs and feel like I'm not missing out on anything, I just use APIs directly or CLIs. I honestly don't quite see the point of MCPs any longer.

Yup, but with some caveat. For things like backstage, which have MCP servers but are really fucking insecure, we have a wrapper API that is then linked to a skill.

Over the past 3 months we've been using it a LOT. I made one for our admins so they can work with the CMS and get statistics in their client, the statistics part has been a huge unlock. The big advantage here is that a normal API, direct tool integration or CLI are unpractical to set up for my less technical coworkers.

Other then that I've been building MCP's in pretty much all (personal) tools I'm making now, it's very useful to have a central way for an agent to look at production data without having to ssh into a server.

For some of my projects I use it instead of a CMS. I still have that CMS, but I rarely use it anymore.

Could I have used an API? Maybe. But Laravel MCP makes it very easy to run a MCP server.

i’m a day or two from releasing my programming language’s new mcp

I am not using MCP in be production- but, my team is. My team also produces MCP servers for other teams, and I find it a bit maddening. I wonder if anyone can relate to my experience here.

It feels like there is a significant amount of baggage with MCP. It had first mover advantage- coming in at a time when the frontier looked much different. Models were significantly less predictable, would consistently screw up tool calls- and couldn't quickly find a good path to interfacing directly with an API.

Things are much different now- and I'm frustrated to see that new projects on my team still consider MCP as a reasonable first pass solution for getting data in front of a model. Everyone uses Claude Code (cli, desktop; I also am frustrated that so many people use CC over alternatives- that's another rant) and thus, everyone has an harness that'll happily leverage shell + skills to get things done precisely. So- why? Why is it that I see my team-mates all using the same Atlassian MCP server that's flawed- which we don't control the tool surface of? Why not point an agent at the API spec? If the answer is that it's too slow to startup, having to read the API spec to figure out what to do- then, point it at your .claude/.codex/.whatever directory- find where the agent has used tools from the MCP server, and create skills or some thin client surface.

And I will grant that yes, I have observed that a well-engineered MCP server can offer better performance than giving an agent a loosely defined task to perform with an API. However- 'well-engineered' is not easy to achieve. You must run many iterations of benchmarks and evaluations, observe trajectories, and improve the tool surface over many iterations. You also cannot predict users- so you need to monitor the usage, and improve over time. It's a heavy lift.

Additionally- no-one is benchmarking this stuff. They throw MCP at the problem, and call it a day once an agent can achieve the task. Frustrating.

I tried for a while to speak up and suggest that maybe MCP might not be worth the effort compared to improving the UX (or, AX) of API surfaces, or instead putting cycles towards better data storage and presentation. But I find that I'm starting to feel like a dick for bringing vocalizing this consistently when MCP is mentioned.

I realize this is deep into rant territory by this point. However, anonymous posting on the internet can be good for the soul. Anyway- it generally feels as though others are not as interested as I am in eating their pride, generating research, and improving what we know, and how we do things. This goes back to CC- I am the only member of my team that is not using CC as their daily driver. Again- I feel like a dick, but my god, I sound like a broken record suggesting that others try different models and harnesses. I hear constant half-complaints about verbosity of output, or churn- and barely anyone has been willing to give OpenAI models a spin.

I can't bear to hear a group pity-party about how model output is exhausting to read- when the complaints are exclusive to Anthropic models, and no-one has even read the prompting guidance which states clearly how to drop the verbosity/density/flowery-ness of output.

And for the love of god. Stop trying to make models from other providers work in CC. It is not impossible; but it is by nature, a hacking-unfriendly platform. I promise you that CC cli is not the only coding-agent cli tool that you will feel comfortable using. Actually- I'm willing to double down and bet that you will loathe CC cli once you see what the grass looks like out of that orange walled garden. Bah!

-

Edit: AND! What's the obsession with these (https://artificialanalysis.ai/articles/search-api) products? What's wrong with: https://platform.claude.com/docs/en/agents-and-tools/tool-us... and https://developers.openai.com/api/docs/guides/tools-web-sear... (or, OpenAI's alpha/search endpoint)

Dead tech