- Do you work in a team context of 10+ engineers?
- Do you all use different agent harnesses?
- Do you need to support the same behavior in ephemeral runtimes (GH Agents in Actions)?
- Do you need to share common "canonical" docs across multiple repos?
- Is it your objective to ensure a higher baseline of quality and output across the eng org?
- Would your workload benefit from telemetry and visibility into tool activation?
If none of those apply, then it's not for you. Server hosted MCP over streamable HTTP benefits orgs and teams and has virtually no benefit for individuals.
What I want to know is what's the difference between a remote mcp and an api with an openapi.json endpoint for self-discovery? It's just as centralized
It's instructive to skim the top level of the MCP spec to get a sense. But you can also scroll to the end of the post and see the three .gifs there and see why MCP: because it also defines interaction models with the clients and exposes MCP prompts as `/` (slash) commands and MCP resources as `@` (at) references among other things.
You are right: MCP tools are in essence OpenAPI specs with some niceties like standardized progress reporting. But MCP is more than tools.
I've managed to ignore MCP servers for a long time as well, but recently I found myself creating one to help the LLM agents with my local language (Papiamentu) in the dialect I want.
I made a prolog program that knows the valid words and spelling along with sentence conposition rules.
Via the MCP server a translated text can be verified. If its not faultless the agent enters a feedback loop until it is.
The nice thing is that it's implemented once and I can use it in opencode and claude without having to explain how to run the prolog program, etc.
I can't go into specifics about exactly what I'm doing but I can speak generically:
I have been working on a system using a Fjall datastore in Rust. I haven't found any tools that directly integrate with Fjall so even getting insight into what data is there, being able to remove it etc is hard so I have used https://github.com/modelcontextprotocol/rust-sdk to create a thin CRUD MCP. The AI can use this to create fixtures, check if things are working how they should or debug things e.g. if a query is returning incorrect results and I tell the AI it can quickly check to see if it is a datastore issue or a query layer issue.
Another example is I have a simulator that lets me create test entities and exercise my system. The AI with an MCP server is very good at exercising the platform this way. It also lets me interact with it using plain english even when the API surface isn't directly designed for human use: "Create a scenario that lets us exercise the bug we think we have just fixed and prove it is fixed, create other scenarios you think might trigger other bugs or prove our fix is only partial"
One more example is I have an Overmind style task runner that reads a file, starts up every service in a microservice architecture, can restart them, can see their log output, can check if they can communicate with the other services etc. Not dissimilar to how the AI can use Docker but without Docker to get max performance both during compilation and usage.
Last example is using off the shelf MCP for VCS servers like Github or Gitlab. It can look at issues, update descriptions, comment, code review. This is very useful for your own projects but even more useful for other peoples: "Use the MCP tool to see if anyone else is encountering similar bugs to what we just encountered"
Its very similar to the switch from a text editor + command line, to having an IDE with a debugger.
the AI gets to do two things:
- expose hidden state
- do interactions with the app, and see before/after/errors
it gives more time where the LLM can verify its own work without you needing to step in. Its also a bit more integration test-y than unit.
if you were to add one mcp, make it Playwright or some similar browser automation mcp. Very little has value add over just being able to control a browser
That's also one of the things that worries me the most. What kind of data is being sent to these random endpoints? What if they to rogue or change their behavior?
mcp is generally a static set of tools, where auth is handled by deterministic code and not exposed to the agent.
the agent sees tools as allowed or not by the harness/your mcp config.
For the most part, the same company that you're connecting to is providing the mcp, so its not having your data go to random places, but you can also just write your own. its fairly thin wrappers of a bit of code to call the remote service, and a bit of documentation of when/what/why to do so
That's false. The Amiga could run the Mac OS better than any Mac could, even with the same CPU because of the Amiga custom chips. Also, Amigas had faster CPUs available than the Macs did, and the Amiga OS was still multitasking in the background.
I’ll laugh whenever someone comes along and says "This is definitely an act of war" despite everything we’ve all seen that has been done to Iran lately.
Trailers work with unrefined oil. There isn’t much difference between a truck trailer and an oil tanker car on the railway.
Difference is size and cost per unit to move it. We are talking about Middle East light sweet crude oil here, not Alberta’s oil sands or whatnot which does require some processing and heating even before sending it through a pipeline.
North Dakota currently sends a few trainloads of crude oil directly from the fields to refiners 50 miles away from me today. Tanker trucks do routes picking up a few dozen barrels per rig every few days/weeks/months in low producing areas of the country.
The engine isn't in the trailer. That is in the tractor, which pulls a trailer.
If OP meant "fueled by unrefined oil" then sure, but I didn't even consider that to be an option.
The heavier crude grades cannot be (realistically, at least) put into trailers or tanker cars - which is what I thought was being implied here for the Gulf oil sources.
I suspect it got flagged by the people who think it was written by an LLM, and the people who thought the "jealousy" argument was particularly weak. It's also a lot of words when the answer is obvious (as pointed out by many commenters here): Money.
Since the development of computers, companies have wanted to save money and that's meant a push to find a magic bullet that can replace many, if not most or all, programmers. Natural language programming, RAD tools, much of the work on fifth-generation languages, was oriented around that objective (removing or reducing the dependence on programmers as a category of professionals, versus domain experts who happen to also program).
Biased as the submitter here, but even if "jealousy" may be a weak argument (as presented) some of us were discussing scenarios where jealous statements were too obvious to let slide. It's a real human emotion and adds an unexplored angle.
I mean, yeah. Epstein isn't an abberation, he's typical C-level management. They say "power corrupts", but I think it warps social reality. They're all complicit in the maintainance of a political economy that facilitates the concentration of power in a way that obviates consent.
I code in 8 languages, regularly, for several open source and industry projects.
I use AI a lot nowadays, but have never ever interacted with an MCP server.
I have no idea what I'm missing. I am very interested in learning more about what do you use it for.
reply