I still prefer MCP over skills

Don't focus on what you prefer: it does not matter. Focus on what tool the LLM requires to do its work in the best way. MCP adds friction, imagine doing yourself the work using the average MCP server. However, skills alone are not sufficient if you want, for instance, creating the ability for LLMs to instrument a complicated system. Work in two steps:

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.

The most common mistake that I see here is people thinking only MCP can be bound to a server and store secrets and be called remotely

No, a CLI with RPC can do exactly that, just smaller. It goes lower in the exact same stack without the fluff.

This argument always sounds like two crowds shouting past each other.

Are you a solo developer, are you fully in control of your environment, are you focused on productivity and extremely tight feedback loops, do you have a high tolerance for risk: you should probably use CLIs. MCPs will just irritate you.

Are you trying to work together with multiple people at organizational scale and alignment is a problem; are you working in a range of environments which need controls and management, do you have a more defensive risk tolerance ... then by the time you wrap CLIs into a form that are suitable you will have reinvented a version of the MCP protocol. You might as well just use MCP in the first place.

Aside - yes, MCP in its current iteration is fairly greedy in its context usage, but that's very obviously going to be fixed with various progressive-disclosure approaches as the spec develops.

I could not agree any less with the author. I don’t want APIs, I want agents to use the same CLI tooling I already use that is locally available. If my agents are using CLI tooling anyways there is no need to add an extra layer via MCP.

I don’t want remote MCP calls, I don’t even want remote models but that’s cost prohibitive.

If I need to call an API, a skill with existing CLI tooling is more than capable.

I think language grammars are the an interesting way to define a ruleset too. Forget REST API's or MCP Servers for a second... Define a domain specific language, and let the language model generate a valid instruction within the confines of that grammar.

Than pass the program, your server or application can parse the instructions and work from the generated AST to do all sorts of interesting things, within the confines of your language features.

It's verifiable, since you are providing within the defined grammar, and with the parser provided.

It is implicitly sandboxed by the powers you give (or rather exclude) to your runtime via an interpreter/compiler

I've tried this before for a grammar I defined for searching documents, and found it to be quite good at creating valid often complex search instructions.

I like skills because they rely on the same tools which humans rely upon. A well-written skill can be read and used by a human too.

A skill is just a description for how to use an existing CLI tool. You don't need to write new code for the LLM to interact with some system. You just tell the LLM to use the same tool humans do. And if you find the CLI is lacking in some way, you can improve it and direct human usage benefits from that improvement too.

On the other hand, an MCP requires implementing a new API for a service, an API exclusive to LLMs, and keeping parallel documentation for that. Every hour of effort put into it is an hour that's taken away from improving the human-facing API and documentation.

The way skills are lazy-loaded when needed also keeps context clean when they're not used. To be fair, MCPs could be lazy-loaded the same way, that's just an implementation detail.

This isn't a zero-sum game or a choice of one over the other. They solve different layers of the developer experience: MCP provides a standardized, portable interface for external data/tools (the infrastructure), while Skills offer project-specific, high-level behavioral context (the orchestration). A robust workflow uses MCP to ensure tool reliability and Skills to define when and how to deploy those tools.

Scanning through the comments here I am almost certain the majority of people in this thread run coding agents on-device. Skills that access already available resources is then more convenient and you can easily make the argument that it is more agronomic.

That being said, majority of users on this planet don't use AI agents like that. They go to ChatGPT or equivalent. MCP in this case is the obvious choice because it provides remote access and it has better authentication story.

In order to make any argument about pro/con of MCP vs Skills you first need to find out who is the user.

Surprised to see no mention in the article or discussion yet about using MCPs in 'code mode', where an API is generated client-side relying on MCP primarily as an interface standard. I'm still learning but I've read this reduces the amount of context required to use the MCP.

It seems like a lot of the discussion is arguing in favor of API usage without realizing that MCP basically standardizes a universal API, thus enabling code mode.

For my use I prefer just a raw CLI. As long as it's built following conventions (e.g. using cobra for a Go app) then the agent will just natively know how to use it, by which I mean how to progressively learn what it needs by reading the `help` output. In that case you don't need a skill or anything. Just say "I want this information, use the xyz app". It will then try `xyz --help` or `xyz help` or a variant, just like a human would, see the subcommands, do `xyz help subcommand` and eventually find what it needs to do the job. Good tools provide an OAuth flow like `xyz login`, which will open a browser window where you can determine which resources you want to give the CLI (and thereby the agent) access to.

This only works for people using agents themselves on computers they control, rather than, e.g., the Claude web app, but is a good chunk of my usage.

I think people are either over or under thinking the auth piece, though. The agent should have access to their own token. Both CLIs and MCPs and even raw API requests work this way. I don't think MCPs provide any further security. You should assume the agent can access anything in its environment and do everything up to what the credential permits. You don't want to give your more powerful credential to the MCP server and hope that the MCP server somehow restricts the agent to doing less (it can probably find the credential and make out-of-band calls if it wants). The only way I think it could work like that is how... is it Sprite does it?... where you give use a fake token and have an off-machine proxy that it goes through where it MitMs the request and injects the real credential.

One thing that I have found is that the platforms are surprisingly poor at consistently implementing MCP, which is actually a pretty simple protocol.

Take Codex, for example, it does not support the MCP prompts spec[0][1] which is quite powerful because it solves a lot of friction with deploying and synchronizing SKILL.md files. It also allows customization of virtual SKILL.md files since it allows compositing the markdown on the server.

It baffles me why such a simple protocol and powerful capability is not supported by Codex. If anyone from OpenAI is reading this, would love to understand the reasoning for the poor support for this relatively simple protocol.

[0] https://github.com/openai/codex/issues/5059

[1] https://modelcontextprotocol.io/specification/2025-06-18/ser...

I agree for a slightly different reason - human stupidity.

Despite many decades of proof that automation simplifies and reveals the illogical in organisations, digitisation has mostly stopped at below the “CXO” level - and so there are not APIs or CLIs available to anyone - but MCP is cutting through

Just consider:

Throughout companies large and small, Agile is what coders do, real project managers still use deadlines and upfront design of what will be in the deadline - so any attempt to convert the whole company to react to the reality of the road is blocked

Reports flow upwards - but through the reporting chain. So those PowerPoints are … massaged to meet to correct story, and the more levels it’s massaged the more it fails to resemble reality. Everyone knows this but managing the transition means potentially losing control …

There are plenty of digitisationmprojects going on - but do they enable full automation or are they another case of an existing political arena building its own political choices in software - “our area in a database to be accessed via an UI by our people” - almost never “our area to be used by others via API and totally replacing our people”.

(I think I need to be more persuasive

Don't they both solve different problems? This tribalism makes no sense.

The "only skills" people are usually non-technical and the "only CLI" people are often solo builders.

MCP makes a lot of sense for enterprise IMO. Defines auth and interfaces in a way that's a natural extension of APIs.

> Context Bloat: Using a skill often requires loading the entire SKILL.md into the LLM’s context window, rather than just exposing the single tool signature it needs. It’s like forcing someone to read the entire car’s owner’s manual when all they want to do is call car.turn_on().

MCP has severe context bloat just by starting a thread. If harnesses were smart enough to, during install time, summarize the tools provided by a MCP server (rather than dumping the whole thing in context), it would be better. But a worse problem is that the output of MCP goes straight into the context of the agent, rather than being piped somewhere else

A solution is to have the agent run a cli tool to access mcp services. That way the agent can filter the output with jq, store it in a file for analysis later, etc

> The core philosophy of MCP is simple: it’s an API abstraction. The LLM doesn’t need to understand the how; it just needs to know the what.

Wrong. It needs to "understand" both these things. The only difference is where and how the strings explaining them are generated.

Really interesting post. The "connectors vs manuals" framing stuck with me because I think it points at something beyond the UX argument. A Skill that papers over an API loses the signal the friction was carrying. Working with a raw interface tells you something about the design.

The same thing plays out at the language layer. The pain of C++ multiple inheritance drove people toward better abstractions. If LLM's absorb that friction before it reaches anyone, the signal that produces the next Go never gets felt by the people who could act on it.

Wrote about where that leads: https://blog.covet.digital/a/the_last_language_you_can_read....

This frames MCP vs Skills as an either/or, but they operate at different layers. MCP exposes capabilities and Skills may shape how capabilities are used.

Both are useful to different people (and role families) in different ways and if you don't feel certain pain points, you may not care about some of the value they provide.

Agent skills are useful because they're standardized prompt sharing but more than that, because they have progressive disclosure so you don't bloat your context with an inefficietly designed MCP and their UX is very well aligned such that "/SkillBuilder" skills are provided from the start and provide a good path for developers or non traditional builders to turn conversations into semi or full automation. I use this mental model to focus on the iteration pattern and incremental building [1].

[1] https://alexhans.github.io/posts/series/evals/building-agent...

Despite thinking this is AI-generated, I agree but everything has a caveat.

Skills are good for instilling non-repeatable, yet intuitive or institutional knowledge.

MCP’s are great for custom, repeatable tasks. After 5-10 runs of watching my LLM write the same exact script, I just asked it to hardcode the solution and make it a tool. The result is runs are way faster and repeatable.

Occams Razor spares none.

Everything will go to the simplest and most convenient, often both, despite the resistance of the complexity lovers.

Sorry MCP, you are not as simple as CLI/skill/combination, and no, you are not more secure just because you are buried under 3 level of spaghetti. There are no reason for you to exist, just like Copilot. I don't just wish, but know you'll go into obscurity like IE6.

Skills are static; MCP servers is dynamic. Skills codify info and workflows, help decrease redundant instructions, and increase consistent outcomes. MCP servers allow access to changing resources across systems.

You may dislike MCP, and there are certainly valid arguments to be made there, but that doesn't mean you can replace it with skills. If you could replace a given MCP server with a skill it would only indicate that someone misunderstood the assignment and chose the wrong tool in the first place. It wouldn't indicate the superiority of one thing over the other.

This whole article, and it's current rank on HN (#5), is making me feel like I took crazy pills this morning. A colleague suggests this Skills vs MCP discourse is big on Twitter, so maybe I lack the necessary background to appreciate this, but aren't these different tools, solving for different things, in different ways? Is this parody? Am I falling into a bot engagement trap by even responding to this? The article certainly reads like LinkedIn drivel, with vague, emphatic opinions about nothing.

My biggest gripe with skills is that even clear and explicit instructions are regularly ignored - even when the skill is brief (< 100 lines).

I’ll often see the agent saying it’s about to do something so I’ll stop it and ask “what does the xxx skill say about doing that?’ And it’ll go away and think and then say “oh, the skill says I should never do that”

The comparison to app stores is interesting but I think MCP registries solve a different problem. App stores are for humans browsing. MCP registries are for agents discovering tools at runtime based on the task at hand. The user never browses — they describe what they need and the agent finds the tool.

That is a meaningful distribution shift. Products no longer need to be marketed to end users if an agent can find and invoke them directly. Skills require the developer to install them ahead of time, which means someone already decided this tool was relevant.

I think the worse thing is when someone takes a clearly defined list of steps to do something and writes it as a skill rather than just having AI write it as a script. It’s like people have forgot what scripting is

Yeah well. MCPs are better for use cases where remote access is required, but for development use cases what you need in the majority of use cases is to manipulate local files. Skills are just the more natural solution here. You can argue whether Skills should come with more type information (MCPs are slightly better here), but otherwise it seems pretty clear to me that if you do not need remote access then MCPs are not really needed.

For indie developers like myself, I often use chat GPT desktop and Claude desktop for arbitrary tasks, though my main workhorse is a customized coding harness with CC daemons on my nas. With the apps, b I missed having access to my Nas server where my dev environment is. So I wrote a file system MCP and hosted it with a reverse proxy on my Truenas with auth0. I wanted access to it from all platforms CharGPT mobile, desktop. Same for CC.

For chatgpt desktop and Claude desktop my experience with MCPs connected to my home NAS is pretty poor. It(as in the app) often times out fetching data(even though there is no latency for serving the request in the logs), often the existing connection gets invalidated between 2 chat turns and chat gpt just moves on answering without the file in hand.

I am not using it for writing code, its mostly read only access to Fs. Has anyone surmounted these problems for this access patterns and written about how to build mcps to be reliable?

    > ChatGPT can’t run CLIs. Neither can Perplexity or the standard web version of Claude. Unless you are using a full-blown compute environment (like Perplexity Computer, Claude Cowork, Claude Code, or Codex), any skill that relies on a CLI is dead on arrival.

Incorrect observation. Claude web does support skills upload. I guess claude runs code_interpreter tool and filesystem in the background to run user uploaded skills. ChatGPT business plans too allow uploading custom skills in web.

I can see Skills becoming a standard soon. But the concern still holds. When you publish a MCP you liberate the user out of installing anything. But with skills what happens if the skill running environment don't have access to the cli binary or if it isn't in PATH?

I never understood why there is a discussion about it, one or the other… both serve a different purpose and are complementary.

I think the key problem is that usage of MCP servers is not 'baked' into the LLM training - but API's and CLI's are already a part of training. So to use your MCP server, the LLM has to use additional intelligence which could have been used to do the actual work instead.

We had a contention between MCP / Skills for our product and ended up offering both. We built a CLI tool that could interface with the MCP server [1]. It seems redundant but our app is a coding app on iOS (Codea), and the issue with offering a plain MCP server meant that the agentic coding harness found it harder to do its job.

With the CLI the agent could check out the project, work on it locally with its standard file editing / patching / reading tools, then push the work back to device. Run and debug on device, edit locally, push.

With MCP the agent had to query the MCP server for every read and write and was no longer operating in its normal coding loop. It still works, though, and as a user you can choose to bypass the CLI and connect directly via MCP.

The MCP server was valuable as it gave us a consistent and deterministic language to speak. The CLI tool + Skill was valuable for agentic coding because it allowed the coding work to happen with the standard editing tools used by agents.

The CLI also gave us device discovery. So the agent can simply discover nearby devices running Codea and get to work, instead of a user having to add a specific device via its IP address to their agent.

[1] https://codea.io/cli

As others have said I have found CLI tools much better

This is how I am structuring stuff in Claude Code

- Ansible setup github cli, git, atlassian cli, aws-cli, terraform cli tooling

- Claude hooks for checking these cli tools are authenticated and configured

- Claude skills to use the CLI tooling

This is the same as saying "I still prefer hammer over screwdriver".

I use both and don't feel they're mutually exclusive.

E.g. if I have some ElasticSearch cluster, I use a skill to describe the data, and if I ask the LLM to write code that queries ElasticSearch but to test it first it can use a combination of skill + MCP to actually run a query.

I think this model works nicely.

Anthropic says that Skills and MCPs are complementary, and frankly the pure Skills zealots tend to miss that in enterprise environments you’ll have chatbots or the like that don’t have access to a full CLI. It doesn’t matter if your skills tell the agent exactly what to do if they can’t execute the commands. Also, MCP is better for restricted environments because you know exactly what it can or cannot do. That’s why MCP will exist for some time still. They solve distinct problem sets.

There is one area where MCP typically has challenges - Not a technical challenge but a practical challenge.

Imagine you are creating an asset which requires multiple API calls and your UI is designed to go through a 10-12 step setup process for that asset. In practice even if we give one tool for LLM to one-shot it, or even if we break it down into 10-12 tools the points of hallucinations are much higher.

Contrast this with "skills" and CLI.

Different techniques appropriate in different situations, I would decide on what's appropriate given the goals you have. Whichg is nearly always the answer to X is a better way than Y arguments.

100% MCPs truly give the agent tools and allow the agent to make better informed decisions given you can have configured the right MCP tools. Skills are good for knowledge and general guidelines. They give context to the agent, and I have seen some skills being excessively long that could into eat into the context window of the agent. This tool https://protomcp.io/ helps a lot with testing MCP servers before integrating into the agent workflow. You can even see the agent call different tools in real time and view the trace.

This tracks with my experience.

I started out building an MCP server for an internal wiki, but ended up replacing it with a simple CLI + skill because the wiki had no access control and the simpler setup was good enough in practice.

I think that's the important boundary, though: once access control, auth, or per-user permissions enter the picture, I'd much rather have MCP as the interface than rely on local tooling conventions.

>>>The core philosophy of MCP is simple: it’s an API abstraction.

That's exactly the problem. As agents become better and can read API documentation themselves, WHY do you need an API abstraction?

Having developed mantyx.io, I believe that rest apis are still champion. MCP is nothing more than rest wrappers most of the time and skills are cli wrappers which in turn are rest wrappers.

I think both will stick around because they solve two different problems. 1) what are you able to do (skills) 2) which tools you have to do it (mcp)

Like saying I prefer websites over CLI, or bicycles over canoes. Chisels over planes. Depends what you are trying to achieve.

Complete in synch with the author MCP and A2A for the win.

CLI is massively superior to MCP in my experience. First, because I also understand what's going on and do it myself if necessary. Second because it's so much cheaper in terms of tokens it's not even funny

Huh, I think the author might be deliberately ignoring how MCP works?

- "CLIs need to be published, managed, and installed" -- same for MCP servers which you have to define in your config, and they frequently use some kind of "npx mcp-whatever" call.

- "Where do you put the API tokens required to authenticate?" -- where does an MCP server put them? In your home folder? Some .env file? The keychain? Same like CLI tools.

- "Some tools support installing skills via npx skills, but that only works in Codex and Claude Code, not Claude Cowork or standard Claude" -- sure, but you also can't universally define MCP servers for all those tools. You have to go ahead and edit the config anyway.

- "Using a skill often requires loading the entire SKILL.md into the LLM’s context window, rather than just exposing the single tool signature it needs" -- yeah, but it's on-demand rather than exposing ALL MCP servers' tool signatures. Have you ever tried to use playwright MCP?

I just don't buy the "without any setup" argument.

the best agent framework in my opinion is Pi. Pi avoids MCP thats a good thing. why assume that the planet will migrate from HTTP to MCP? no, instead lets assume we have client code we can call. we already have a rich ecosystem of HTTP services and packages. and if we assume a rewrite for agents we probably wouldn't come up with MCP but something more powerful.

People in the comments still confused about “agentic development” vs. “agentic development”. One uses the cli best, while the other cannot use a cli very well.

The first is using agents locally to develop.

The second is developing an agent. Not necessarily for coding, mind you. Not even for just text sometimes.

They are different cases, MCP is great for the latter.

I still use vanilla Claude Code without MCP or skills, am I in the minority? Not trying to be a luddite.

Or use both. Remote MCPs are secure, CLI allows for programmatic execution. Use bash to run remote MCPs.

I built this to solve this exact problem. https://github.com/turlockmike/murl