These commands would be well defined and standardised, maybe with a hashed value that could be used to ensure re-usability (think Docker layers).
Then I just have a skill called:
- github-review-slim:latest - github-review-security:8.0.2
MCPs will still be relevant for those tricky monolithic services or weird business processes that aren't logged or recorded on metrics.
- If you need to interact with a local app in a one-off session, then use CLI.
- If you need to interact with an online service in a one-off session, then use their API.
- If you need to interact with a local app in a persistent manner, and if that app provides an MCP server, use it.
- If you need to interact with an online service in a persistent manner, and if that app provides an MCP server, use it.
Whether the MCP server is implemented well is a whole other question. A properly configured MCP explains to the agent how to use it without too much context bloat. Not using a proper MCP for persistent access, and instead trying to describe the interaction yourself with skill files, just doesn't make any sense. The MCP owner should be optimizing the prompts to help the agent use it effectively.
MCP is the absolute best and most effective way to integrate external tools into your agent sessions. I don't understand what the arguments are against that statement?
MCP is more for a back and forth communication between agent and app/service, or for providing tool/API awareness during other tasks. Like MCP for Jira would let the AI know it can grab tickets from Jira when needed while working on other things.
I guess it's more like: the MCP isn't for us - it's for the agent to decide when to use.
Where I DO see MCPs getting actual use is when the auth story for something (looking at you slack, gmail, etc) is so gimped out that basically, regular people can't access data via CLI in any sane or reasonable way. You have to do an oauth dance involving app approvals that are specifically designed to create a walled garden of "blessed" integrations.
The MCP provider then helpfully pays the integration tax for you (how generous!) while ensuring you can't do inconvenient things like say, bulk exporting your own data.
As far as I can tell, that's the _actual_ sweet spot for MCPs. They're sort of a technology of control, providing you limited access to your own data, without letting you do arbitrary compute.
I understand this can be considered a feature if you're on the other side of the walled garden, or you're interested in certain kinds of enterprise control. As a programmer however I prefer working in open ecosystems where code isn't restricted because it's inconvenient to someone's business model.
I think this is the key; I want my analysts to be able to access 40% of the database they need to do their job, but not the other 60% parts that would allow them to dump the business-secrets part of the db, and start up business across the street. You can do this to some extent with roles etc but MCP in some ways is the data firewall as your last line of protection/auth.
I encountered a similar scenario using Atlassian MCP recently, where someone needed to analyse hundreds of Confluence child pages from the last couple of years which all used the same starter template - I gave the agent a tool to let it call any other tool in batch and expose the results for subsequent tools to use as inputs, rather than dumping it straight into the context (e.g. another tool which gives each page to a sub-agent with a structured output schema and a prompt with extraction instructions, or piping the results into a code execution tool).
It turned what would have been hundreds of individual tool calls filling the context with multiple MBs of raw confluence pages, into a couple of calls returning relevant low-hundreds of KBs of JSON the agent could work further with.
What it can do is call multiple MCPs, dumping tons of crap into the context and then separately run some analysis on that data.
Composable MCPs would require some sort of external sandbox in which the agent can write small bits of code to transform and filter the results from one MCP to the next.
Maybe I'm misunderstanding the definition of composability, but it sounds like your issue isn't that MCP isn't composable, but that it's wasteful because it adds data from interstitial steps to the context. But there are numerous ways to circumvent this.
For example, it wouldn't be hard to create a tool that just runs an LLM, so when the main LLM convo calls this tool it's effectively a subagent. This subagent can do work, call MCPs, store their responses in its context, and thereby feed that data as input into other MCPs/CLIs, and continue in this way until it's done with its work, then return its final result and disappear. The main LLM will only get the result and its context won't be polluted with intermediary steps.
This is pretty trivial to implement.
Context window is expensive and precious. Much better to offload to some medium where it isn’t.
It’s the equivalent to calling CLIs in bash, except mlua is a sandboxes runtime while bash is not.
Tools themselves also cannot be composed in any SOTA models. Composition is not a feature the tool schema supports and they are not trained on it.
Models obviously understand the general concept of function composition, but we don't currently provide the environments in which this is actually possible out side of highly generic tools like Bash or sandboxed execution environments like https://agenttoolprotocol.com/
I totally agree that mcp not being compostable is a very big issue.
I implemented this in an agent which runs in the browser (in our internal equivalent of ChatGPT or Claude's web UI), connecting directly to Atlassian MCP.
So I guess you had to modify the agent harness to do this? or I guess you could use... mcp-cli ... ??
Essentially you give the agent a way to run code that calls MCP servers, then it can use them like any other API.
Nowadays small bash/bun scripts and an MCP gateway proxy gets me the same exact thing.
So yeah at some level you do have to build out your own custom functionality.
This is the same as a CLI. Bash is nothing but a programming language and you can do the same approach by giving the model JavaScript and have it call MCP tools and compose them. If you do that you can even throw in composing it with CLis as well
Nope.
The best way to interact with an external service is an api.
It was the best way before, and its the best way now.
MCP doesn't scale and it has a bloated unnecessarily complicated spec.
Some MCP servers are good; but in general a new bad way of interacting with external services, is not the best way of doing it, and the assertion that it is in general, best, is what I refer to as “works for me” coolaid.
…because it probably does work well for you.
…because you are using a few, good, MCP servers.
However, that doesn't scale, for all the reasons listed by the many detractors of MCP.
Its not that it cant be used effectively, it is that in general it is a solution that has been incompetently slapped on by many providers who dont appreciate how to do it well and even then, it scales badly.
It is a bad solution for a solved problem.
Agents have made the problem MCP was solving obsolete.
- easy tool calling for the LLM rather than having to figure out how to call the API based on docs only. - authorization can be handled automatically by MCP clients. How are you going to give a token to your LLM otherwise?? And if you do, how do you ensure it does not leak the token? With MCP the token is only usable by the MCP client and the LLM does not need to see it. - lots more things MCP lets you do, like bundle resources and let the server request off band input from users which the LLM should not see.
I think the best way to run an agent workflow with custom tools is to use a harness that allows you to just, like, write custom tools. Anthropic expects you to use the Agent SDK with its “in-process MCP server” if you want to register custom tools, which sounds like a huge waste of resources, particularly in workflows involving swarms of agents. This is abstraction for the sake of abstraction (or, rather, market share).
Getting the tool built in the first place is a matter of pointing your agent at the API you’d like to use and just have them write it. It’s an easy one-shot even for small OSS models. And then, you know exactly what that tool does. You don’t have to worry about some update introducing a breaking change in your provider’s MCP service, and you can control every single line of code. Meanwhile, every time you call a tool registered by an MCP server, you’re trusting that it does what it says.
> authorization can be handled automatically by MCP clients. How are you going to give a token to your LLM otherwise??
env vars or a key vault
> And if you do, how do you ensure it does not leak the token?
env vars or a key vault
Now let's say you want all your Claude Code sessions to use this calendar app so that you can always say something like "ah yes, do I have availability on Saturday for this meeting?" and the AI will look at the schedule to find out.
What's the best way to create this persistent connection to the calendar app? I think it's obviously an MCP server.
In the calendar app I provide a built-in MCP server that gives the following tools to agents: read_calendar, and update_calendar. You open Claude Code and connect to the MCP server, and configure it to connect to the MCP for all sessions - and you're done. You don't have to explain what the calendar app is, when to use it, or how to use it.
Explain to me a better solution.
Then, the minimal skill descriptions are always in the model's context, and whenever you ask it to add something to the calendar, it will know to fetch that skill. It feels very similar to the MCP solution to me, but with potentially less bloat and no obligation to deal with MCP? I might be missing something, though.
Connected MCP tools are also always in the model's context, and it works for any AI agent that supports MCP, not just Claude Code.
So does an API and a text file (or hell, a self describing api).
Which is more complex and harder to maintain, update and use?
This is a solved problem.
The world doesnt need MCP to reinvent a solution to it.
If we’re gonna play the ELI5 game, why does MCP define a UI as part of its spec? Why does it define a bunch of different resource types of which only tools are used by most servers? Why did not have an auth spec at launch? Why are there so many MCP security concerns?
These are not idle questions.
They are indicative of the “more featurrrrrres” and “lack of competence” that went into designing MCP.
Agents, running a sandbox, with normal standard rbac based access control or, for complex operations standard stateful cli tooling like the azure cli are fundamentally better.
Self-describing APIs require probing through calls, they don't tell you what you need to know before you interact with them.
MCP servers are very simple to implement, and the developers of the app/service maintain the server so you don't have to create or update skills with incomplete understanding of the system.
Your skill file is going to drift from the actual API as the app updates. You're going to have to manage it, instead of the developers of the app. I don't understand what you're even talking about.
…
> Let's say I made a calendar app that stores appointments for you. It's local, installed on your system,
> and the developers of the app/service maintain the server so you don't have to create or update skills
…
> I don't understand what you're even talking about.
You certainly do not.
Show me you can stop doing that, and I'll happily mediate a technical version of this conversation that proceeds respectfully from the two of you each making a clear and concise statement of your design thesis, and what you see as its primary pros and cons.
For that I'll take a flat $150 for up to 4 hours. I usually bill by the 15-minute increment, but obviously we would dispense with that here, and ordinarily I would not, of course, offer such a remarkable discount. But it doesn't really take $150 worth of effort to remind someone that he should take better care to distinguish his engineering judgment and his outraged insecurity.
More than anything I'm getting frustrated with HN discussions because people just insinuate that I'm stupid instead of making substantive arguments reasoning how what I'm saying is wrong.
Are we performing for an audience or having a discussion?
I understand why this website doesn't have DMs except among YC founders. But if it were otherwise, I'd have DMed you instead of posting that first comment publicly. The criticism I remain convinced has merit, but such things are better done in private. If I chose to make an example out of you over the other guy, it was because you looked like offering a better chance than he of redirecting this into the kind of discussion from which someone could conceivably learn something.
That sounds great. How about we standardize this idea? We can have an endpoint to tell the agents where to find this text file and API. Perhaps we should be a bit formal and call it a protocol!
Good news! It's already standardized and agents already know where to find it!
It's not a choice between Skills or MCP, you can also just create your own tools, in whatever language you want, and then send in the tool info to the model. The wiring is trivial.
I write all my own tools bespoke in Rust and send them directly to the Anthropic API. So I have tools for reading my email, my calendar, writing and search files etc. It means I can have super fast tools, reduce context bloat, and keep things simple without needing to go into the whole mess of MCP clients and servers.
And btw, I wrote my own MCP client and server from the spec about a year ago, so I know the MCP spec backwards and forwards, it's mostly jank and not needed. Once I got started just writing my own tools from scratch I realised I would never use MCP again.
MCPs needs to be wrapped to be composed.
MCPs needs to implement stateful behavior, shell + cli gives it to you for free.
MCP isn't great, the main value of it is that it's got uptake, it's structured and it's "for agents." You can wrap/introspect MCP to do lots of neat things.
"MCPs needs to be wrapped to be composed." -> Also not true anymore, Claude Code or Cowork can chain MCP calls, and any agent using bash can also do it with mcpc
"MCPs needs to implement stateful behavior, shell + cli gives it to you for free." -> having a shell+cli running seems like a lot more work than adding a sessionId into an MCP server. And Oauth is a lot simpler to implement with MCP than with a CLI.
MCP's biggest value today is that it's very easy to use for non-tech users. And a lot of developers seem to forget than most people are not tech and CLI power users
* What algorithm does tool_search use?
* Can tool_search search subcommands only?
* What's your argument for a harness having a hacked in bash wrapper nestled into the MCP to handle composition being a better idea than just using a CLI?
* Shell + CLI gives you basically infinite workflow possibilities via composition. Given the prior point, perhaps you could get a lot of that with hacked-in MCP composition, but given the training data, I'll take an agent's ability to write bash scripts over their ability to compose MCPs by far.
"MCPs needs to implement stateful behavior" - also doesn't make any sense. Why would an MCP need to implement stateful behavior? It is essentially just an API for agents to use.
tool --help
tool subcommand1 --help
tool subcommand2 --help
man tool | grep "thing I care about"
As for stateful behavior, say you have the google docs or email mcp. You want to search org-wide for docs or emails that match some filter, make it a data set, then do analysis. To do this with MCP, the model has to write the files manually after reading however many KB of input from the MCP. With a cli it's just "tool >> starting_data_set.csv"
You can implement progressive disclosure in MCP as well by implementing those same help commands as tools. The MCP should not be providing thousands of tools, but the minimum set of tools to help the AI use the service. If your service is small, you can probably distill the entire API into MCP tools. If you're AWS then you provide tools that then document the API progressively.
Technically, you could have an AWS MCP provide one tool that guides the AI on how to use specific AWS services through search/keywords and some kind of cursor logic.
The entire point of MCP is inherent knowledge of a tool for agentic use.
Completely false. I was dealing with this problem recently (a few tools, consuming too many tokens on each request). MCP has a mechanism for dynamically updating the tools (or tool descriptions):
https://code.claude.com/docs/en/mcp#dynamic-tool-updates
We solved it by providing a single, bare bones tool: It provides a very brief description of the types of tools available (1-2 lines). When the LLM executes that tool, all the tools become available. One of the tools is to go back to the "quiet" state.
That first tool consumes only about 60 tokens. As long as the LLM doesn't need the tools, it takes almost no space.
As others have pointed out, there are other solutions (e.g. having all the tools - each with a 1 line description, but having a "help" tool to get the detailed help for any given tool).
In fact there is: https://platform.claude.com/docs/en/agents-and-tools/tool-us...
If the special tool search tool is available, then a client would not load the descriptions of the tools in advance, but only for the ones found via the search tool. But it's not widely supported yet.
Further, isn't a decorator in Python (like @mcp.tool) the easy way to expose what is needed to an API, if even if all we are doing is building a bridge to another API? That becomes a simple abstraction layer, which most people (and LLMs) get.
Writing a CLI for an existing API is a fool's errand.
I don't think your opinion is reasonable or well grounded. A CLI app can be anything including a script that calls Curl. With a CLI app you can omit a lot of noise from the context things like authentication, request and response headers, status codes, response body parsing, etc. you call the tool, you get a response, done. You'd feel foolish to waste tokens parsing irrelevant content that a deterministic script can handle very easily.
Isn't the same true of filtering tools available thru mcp?
The mcp argument to me really seems like people arguing about tabs and spaces. It's all whitespace my friends.
Well, these will fail for a large amount of cli tools. Any and all combinations of the following are possible, and not all of them will be available, or work at all:
tool some tools may output usage when no arguments are supplied
tool -h some tools may have a short switch for help
tool --help some tools may have a long switch for help
tool help some tools may have help as a subcommand
tool command some tools may output usage for a command with no arguments
tool command -h some tools may have a short switch for command help
tool command --help some tools may have a long switch for command help
tool help command some tools may have a help command
man tool some tools may have man pages
examples: grep one-line usage and "type grep --help"
grep -h one-line usage and "type grep --help"
grep --help extended usage docs
man grep very extended usage docs
python starts interactive python shell
python -h
python --help equivalent help output
ps short list of processes
ps -h longer list of processes
ps --help short help saying you can do, for example, `ps --help a`
ps --help a gives an extended help, nothing about a
erl
erl -h
erl --help all three start Erlang shell
man erl No manual entry for erl
etc.Not to say that MCPs are any better. They are written by people, after all. So they are as messy.
Knowledge about any MCP is not something special inherent in the LLM, it's just an agent side thing. When it comes to the LLM, it's just some text injected to its prompting, just like a CLI would be.
So I run the agent in a VM (it's faster, which I find concerning), and run an MCP on the host that the guest can access, with the MCP also only containing commands that I'm okay with the agent deciding to run.
Despite my previous efforts with skills, I've found agents will still do things like call help on CLIs and find commands that it must never call. By the delights of the way the probabilities are influenced by prompts, explicitly telling it not to run specific commands increases the risk that it will (because any words in the context memory are more likely to be returned).
Honestly, an agent shouldn’t really care how it’s getting an answer, only that it’s getting an answer to the question it needs answered. If that’s a skill, API call, or MCP tool call, it shouldn’t really matter all that much to the agent. The rest is just how it’s configured for the users.
I wrap all my apis in small bash wrappers that is just curl with automatic session handling so the AI only needs to focus on querying. The only thing in the -h for these scripts is a note that it is a wrapper around curl. I havent had a single issue with AI spinning its wheels trying to understand how to hit the downstream system. No context bloat needed and no reinventing the wheel with MCP when the api already exists
Having service providers implement MCP saves everyone from having to do that work themselves.
Plus there are a lot more uses cases than developers running agents on their own machine.
```
#!/usr/bin/env bash
creds={path to creds}
basepath={url basepath}
url={parse from args}
curl -H "Authorization: #{creds}" "#{basepath}/#{url}" $rest_of_args
```Just a way to read/set the auth and then calling curl. Its generalizable to nearly all apis out there. It requires no work by the provider and you can shape it however you need.
How about driving the same truck without that half ton of water?
- Skills help the LLM answer the "how" to interact with API/CLIs from your original prompt
- API is what actually sends/receives the interaction/request
- CLI is the actual doing / instruct set of the interaction/request
- MCP helps the LLM understand what is available from the CLI and API
They are all complementary.
I noticed that LLMs will tend to work by default with CLIs even if there's a connected MCP, likely because a) there's an overexposure of CLIs in training data b) because they are better composable and inspectable by design so a better choice in their tool selection.
Why on earth don't people understand that MCP and skills are complementary concepts, why? If people argue over MCP v. Skills they clearly don't understand either deeply.
Future version of the protocol can easily expose skills so that MCPs can acts like hubs.
The shoe is the sign. Let us follow His example!
Cast off the shoes! Follow the Gourd!
No appetite for that. The MCP vs Skills debate has gradually become just a proxy war for the camps of AI skeptics vs AI boosters. Both sides view it as another chance to decide about more magic vs less, in absolute terms, without doing the work of thinking about anything situational. Nuance, questions, reasoning from first principles, focusing on purely engineering considerations is simply not welcome. The extreme factions do tend to agree that it might be a good idea to attack the middle though! There's no changing this stuff, so when it becomes tiresome it's time to just leave the HN comment section.
I completely agree with you. There was a recent finding that said Agents.md outperforms skills. I'm old school and I actually see best results by just directly feeding everything into the prompt context itself.
https://vercel.com/blog/agents-md-outperforms-skills-in-our-...
edit: just want to add, i still haven't implemented a single mcp related thing. Don't see the point at all. REST + Swagger + codegen + claude + skills/tools works fine enough.
Start with a simple "Let me build a script for claude that can rename the namespace for all the file in a folder". If you have 100K+ plus files, it effort is worth it and your tools start getting chained together too. So make sure each tool only has one purpose for existing and that its output is perfect. So when claude start chaining them and you see what is possible, the mind opens up even more to possibilities.
How? Jetbrains in a Java code baes is amazing and very thorough on refactors. I can reliably rename, change signature, move things around etc.
What if you don’t want the AI to have any write access for a tool? I think the ability to choose what parts of the tool you expose is the biggest benefit of MCP.
As opposed to a READ_ONLY_TOOL_SKILL.md that states “it’s important that you must not use any edit API’s…”
Safer than just giving an instruction to use the tool a specific way.
In this context, the MCP interface acts as a privilege-limiting proxy between the actor (LLM/agent) and the tool, and it's little different from the standard best practice of always using accounts (and API keys) with the minimum set of necessary privileges.
It might be easier in practice to set up an MCP server to do this privilege-limiting than to refactor an API or CLI-tool, but that's more an indictment of the latter than an endorsement of the former.
low quality troll
Perhaps the title is just clickbait. :)
> for each desired change, make the change easy (warning: this may be hard), then make the easy change - Kent Beck
Looking forward, the future is ad-hoc disposable software that once would take a large team a dozen sprints to release.
Eventually it'll be use case -> spec -> validation -> result.
The tv show Stargate showed different controls that scientifically calculated and operated starships so all the operator had to do was point the controls in the direction of the destination. The ai/computer/hardware knows how to get to the result and that result is human driven.
I have evidence of this at work and in my own life with the key component being the tooling integration.
> a difference between local skill and remote MCP
A local skill is a text file with a bunch of explanations of what to do and how, and what pitfalls to avoid. An MCP is a connection to an API that can perform actions on anything. This is a pretty massive difference in terms of concept and I don't think it can be abstracted away. A skill may require an MCP be available to it, for instance, if it's written that way.
Antirez' advice is what I've been doing for a year: use AI to write proper, domain-specific tools that you and it can then use to do more impressive things.
And I still think ppl dont understand why MCPs are still needed and when to use them.
Its actually pretty simple.
1. Ask the LLM to build a tool, under your guide and specification, in order do a specific task. For instance, if you are working with embedded systems, build some monitoring interface that allows, with a simple CLI, to do the debugging of the app as it is working, breakpoints, to spawn the emulator, to restart the program from scratch in a second by re-uploading the live image and resetting the microcontroller. This is just an example, I bet you got what I mean.
2. Then write a skill file where the usage of the tool at "1" is explained.
Of course, for simple tasks, you don't need the first step at all. For instance it does not make sense to have an MCP to use git. The agent knows how to use git: git is comfortable for you, to use manually. It is, likewise, good for the LLM. Similarly if you always estimante the price of running something with AWS, instead of an MCP with services discovery and pricing that needs to be queried in JSON (would you ever use something like that?) write a simple .md file (using the LLM itself) with the prices of the things you use most commonly. This is what you would love to have. And, this is what the LLM wants. For complicated problems, instead, build the dream tool you would build for yourself, then document it in a .md file.