Is this article from a while back?
> Before your agent can do anything useful, it needs to know what tools are available. MCP’s answer is to dump the entire tool catalog into the conversation as JSON Schema. Every tool, every parameter, every option.
Because this simply isn't true anymore for the best clients, like Claude Code.
Similar to how Skills were designed[1] to be searchable without dumping everything into context, MCP tools can (and does in Claude Code) work the same way.
See https://www.anthropic.com/engineering/advanced-tool-use and https://x.com/trq212/status/2011523109871108570 and https://platform.claude.com/docs/en/agents-and-tools/tool-us...
[1] https://agentskills.io/specification#progressive-disclosure
The best things about AI hypergrowth is the opportunities to discover of meta-frameworks and workflows. This is something Anthropic kills at (MCPs, Skills, Claude Code terminal agents).
These are discoveries of workflows. Some of them work some of them don’t. The ones that really click, they explode in popularity like OpenClaw.
After reading Cloudflare's Code Mode MCP blog post[1] I built CMCP[2] which lets you aggregate all MCP servers behind two mcp tools, search and execute.
I do understand anthropic's Tool Search helps with mcp bloat, but it's limited only to claude.
CMCP currently supports codex and claude but PRs are welcome to add more clients.
[1]https://blog.cloudflare.com/code-mode-mcp/ [2]https://github.com/assimelha/cmcp
I have for a lot of my own tools and personal stuff a slightly different approach with this that doesn't use MCP. If you combine skills, with a thin CLI for any API you get a dramatically cheaper version of an MCP and with all the benefits of it just being a simple CLI. Most of the time if I have something like Linear or Hubspot, I just point it at the actual API docs and ask the LLM to make a thin CLI for that API. That way I don't have to load tools for the CLI until needed by a slash command, but the definitions are also tiny so my context stays mostly free.
Hehe... nice one. I think we are all thinking the same thing.
I've also launched https://mcpshim.dev (https://github.com/mcpshim/mcpshim).
The unix way is the best way.
This looks related to Awesome CLIs/TUIs and terminal trove which has lots both CLI and TUI apps.
Awesome TUIs: https://github.com/rothgar/awesome-tuis
Awesome CLIs: https://github.com/agarrharr/awesome-cli-apps
Terminal Trove: https://terminaltrove.com/
I guess this is another one shows that the CLI and Unix is coming back in 2026.
I keep reading these unfair comparisons mixing many different problems into a naive story in favour of clis. First of all no one should still consider connecting mcps directly to agents, this is completely outdated, you connect mcps and tools to a single gateway that has an api, handles federation, auditing, prolicies and much more. A good gateway exposes a tiny minimal context with just instructions how to query what is available and has a configurable "eager" flag for the things that should be put eagerly into the context for certain agent profiles. Secondly many many mcp servers are outdated as they were build for way dumber models than what we have today and will have overly heavy context and descriptions that slow down and degrade the current frontier models. If you compare a cli to a state of the art agent gateway setup with adjustments for the current models, you will find that the only advantage for clis is operational complexity.
I started adding cli's for a few things last week. Initially just for myself but it didn't take me long to figure out that codex / claude code / etc. are pretty good at figuring out cli's as well. And creating them. If you have APIs, generating a usable cli for them is pretty straightforward. With lots of nice features, documentation, bash/zsh autocomplete support and other bells and whistles. Doing that manually is a lot of repetitive work. Having that stuff generated on the other hand doesn't have to take a lot of time.
The combination with skills is where it really shines. And you can generate those as well for your shiny new cli. Once you have that in place, you can drive your API agentically to do non trivial things in it.
One of my OSS projects, jillesvangurp/ktsearch now has such a cli. Ktsearch is a kotlin multiplatform library for Elasticsearch and Opensearch. The new cli compiles to jvm and native linux/mac binaries. I've been playing with this for the last week and adding a few features. It's very nice to have around if you deal with opensearch/elasticsearch clusters. No more messy curl commands and json blobs.
And I've gotten codex to use it for me for a few things already.
I'm looking at this from a slightly different level of abstraction.
The CLI approach definitely has practical benefits for token reduction. Not stuffing the entire schema into the runtime context is a clear win. But my main interest lies less in "token cost" and more in "how we structure the semantic space."
MCP is fundamentally a tool-level protocol. Existing paradigms like Skills already mitigate context bloat and selection overhead pretty well via tool discovery and progressive disclosure. So framing this purely as "MCP vs CLI" feels more like shifting the execution surface rather than a fundamental architectural shift.
The direction I'm exploring is a bit different. Instead of treating tools as the primary unit, what if we normalize the semantic primitives above them (e.g., "search," "read," "create")? Services would then just provide a projection of those semantics. This lets you compress the semantic space itself, expose it lazily, and only pull in the concrete tool/CLI/MCP adapters right at execution time.
You can arguably approximate this with Skills, but the current mental model is still heavily anchored to "tool descriptions"—it doesn't treat normalized semantics as first-class citizens. So while the CLI approach is an interesting optimization, I'm still on the fence about whether it's a real structural paradigm shift beyond just saving tokens.
Ultimately, shouldn't the core question be less about "how do we expose fewer tools," and more about "how do we layer and compress the semantic space the agent has to navigate?"
I feel like the permanent fix is for the AI labs to figure out better attention methods that increase context length without extra inference cost, plus deeper discounts (like -99%) for people being able to add system prompts to their accounts that are cached permanently.
This way you build all your MCPs into the system prompt, save the prompt to the AI provider, then use it without overpaying API costs.
The current "tools-on-demand" workarounds should be great for infrequent tools but the future will probably bring agents with dozens of tools that need them in context to flexibly many of them in the same context window. So we just need to make the context windows longer and make this capability cheaper to use.
Does tool calling in general bloat context, or is there something particular about MCP?
One thing I have read recently is that when you make a tool call it forces the model to go back to the agent. The effect of this is that the agent then has to make another request with all of the prompt (include past messages), these will be "cached" tokens, but they're still expensive. So if you can amortize the tool calls by having the model either do many at once or chaining them with something like bash you'll be better off.
I suspect this might be why cursor likes writing bash scripts so much, simple shell commands are going to be very token heavy because of the frequency of interrupts.
The context window cost is the real story here. Every MCP tool description gets sent on every request regardless of whether the model needs it. If you have 20 tools loaded, that's potentially thousands of tokens of tool descriptions burned before the model even starts thinking about your actual task.
CLI tools sidestep this completely because the agent only needs to know the tool exists and what flags it takes. The actual output is piped and processed, not dumped wholesale into context. And you get composability for free - pipe to jq, grep, head, whatever.
The auth story is where MCP still wins though. If you need a user to connect their Slack or GitHub through a web UI, you need that OAuth dance somewhere. CLI tools assume you already have credentials configured locally, which is fine for developer tooling but doesn't work for consumer-facing AI products.
For developer workflows specifically, I think the sweet spot is what some people are calling SKILL files - a markdown doc that tells the agent what CLI tools are available and when to use them. Tiny context footprint, full composability, and the agent can read the skill doc once and cache it.
True for coding agents running SotA models where you're the human-in-the-loop approving, less true for your deployed agents running on cheap models that you don't see what's being executed.
But yeah, a concrete example is playwright-mcp vs playwright-cli: https://testcollab.com/blog/playwright-cli
In pi coding agent [1] we have the pi-mcp-adapter [2], which provides the best of both worlds.
Like its name says, it implements an adapter pattern, which enables searching and calling out tools from MCPs without overhead. Works like a charm.
[1] https://github.com/badlogic/pi-mono/ [2] https://github.com/nicobailon/pi-mcp-adapter
Not just cheaper in terms of token usage but accuracy as well.
Even the smallest models are RL trained to use shell commands perfectly. Gemini 3 flash performs better with a cli with 20 commands vs 20+ tools in my testing.
cli also works well in terms of maintaining KV cache (changing tools mid say to improve model performance suffers from kv cache vs cli —help command only showing manual for specific command in append only fashion)
Writing your tools as unix like cli also has a nice benefit of model being able to pipe multiple commands together. In the case of browser, i wrote mini-browser which frontier models use much better than explicit tools to control browser because they can compose a giant command sequence to one shot task.
If we use prompt caching - isn't a largish MCP tools section just like a fixed token penalty in return for higher speed at runtime, because tools don't need to be discovered on demand, and that's the better tradeoff? At least for the most powerful models it doesn't feel like their quality goes down much with a few MCP servers. I might be missing something.
It is not better because it invalidates caches.
This article is solving a problem that shouldn't exist in the first place. If you're loading 84 MCP tools into every session, the issue isn't MCP vs CLI, it's that you've turned on everything without thinking about when each tool is actually relevant.
MCP's token cost is the price of availability. The fix isn't to replace the protocol, it's to only activate the tools that matter for the current context. Claude's Skills already work this way -> lightweight descriptions loaded upfront, full definitions fetched on demand. That's essentially the same lazy-loading pattern CLIHub describes, just built into the model's native workflow.
I’m not sure how this works. A lot of that tool description is important to the Agent understanding what it can and can’t do with the specific MCP provider. You’d have to make up for that with a much longer overarching description. Especially for internal only tools that the LLM has no intrinsic context for.
I also prefer CLI over MCP and wrote about it, and why (also when to use #FUSE to integrate AIs and data):
https://www.tabulamag.com/p/a-new-way-to-integrate-data-into
My latest CLI instead of MCP:
MCP's only real value is the auth handshake for third-party SaaS. the actual tool execution is worse than a subprocess call. more tokens, harder to debug, and the failure modes are worse. if someone just extracted the OAuth layer into a standard that CLIs could use, there's very little reason for the rest of the protocol to exist.
So much incorrect and misinformation in these comments. As someone who is building an agent[0] with MCP tools, neither the MCP tool description nor the response is the problem. Both of those are easily solved by not bloating them.
The real killer is the input tokens on each step. If you have 100k tokens in the conversation, and the LLM calls an MCP tool, the output and the existing conversation is sent back. So now you've input 200k tokens to the LLM.
Now imagine 10 tool calls per user message - or 50. You're sending 1-5M input tokens, not because the MCP definitions or tool responses are large, but because at each step, you have to send the whole conversation again.
"what about caching" - Only 90% savings, also cache misses are surprisingly common (we see as low as 40% cache hit rate)
"MCP definitions are still large" - not compared to any normal conversation. Also these get cached
We've seen the biggest savings by batching/parallelizing tool calls. I suspect the future of LLM tool usage will have a different architecture, but CLI doesn't solve the problems either.
[0] https://ziva.sh, it's an agent specialized for Godot[1]
I’m trying to use the CLI whenever possible - it’s much easier to install and can be used by both me and the agent. For example, gh seems much easier than installing and setting up an MCP server connection, and it’s more human-readable in terms of what the agent is calling and what it’s getting in return.
For other integrations, I first try to find an official or unofficial CLI tool (a wrapper around the API), and only then do I consider using MCP
This sounds similar to MCPorter[0], can anyone point out the differences?
If you like me were interested in this but didn't quite know how it'd work, here's a better explanation and examples
https://jannikreinhard.com/2026/02/22/why-cli-tools-are-beat...
These days you can rewrite everything yourself for very cheap. So this is `mcporter` rewritten. I prefer to use Rust personally for rewrites. Opus 4.6 can churn it out pretty quickly if that's what you want. To be honest, almost all software that I want to try these days I don't even install. Instead I'd rather read the README and produce a personal version. This allows encoding idiosyncrasies and specifics that another author will not accept.
The token savings matter, but the bigger win is that models are already trained on CLI patterns. They know how to pipe, grep, jq. MCP is a protocol models had to learn from scratch; CLI is behavior baked into their weights from millions of examples.
I like this approach ... BUT the big win for me is audit logs. CLIs naturally leave a trail you can replay.
ALSO... the permission boundary is clearer. You can whitelist commands, flags, working dir... it becomes manageable.
HOWEVER... packaging still matters. A “small” CLI that pulls in a giant runtime kills the benefit.
I want the discipline of small protocol plus big cache. Cheap models can summarize what they did and avoid full context in every step...
Why are they using JSON in the context? I thought we'd figured out that the extra syntax was a waste of tokens?
Is there any redeeming quality of MCP vs a skill with CLI tool? Right now it looks like the latter is a clear winner.
Maybe MCP can help segregate auto-approve vs ask more cleanly, but I don't actually see that being done.
MCP has some schemas though. CLI is a bit of a mess.
But MCP today isn’t ideal. I think we need to have some catalogs where the agents can fetch more information about MCP services instead of filling the context with not relevant noise.
Awesome stuff. I have a 'root' cli that i namespace stuff into so to remove the need to pass around paths, e.g: `./cli <cmd> ...`
I was just looking for a linear CLI earlier today. Awesome that the CLI converter uses that as an example. Nice!
Just use skills, which allow progressive disclosure of information.
Can LLMs compress those documents into smaller files that still retain the full context?
So it's more of a RAG via CLI than MCP.
MCP servers were a fad, but virtually all of them are completely useless, and often counterproductive for agents that can run code and execute commands directly.
When agents struggle to quickly understand how to use tools, SKILLS provide a far better solution than MCP.
The real issue is that some agents support MCP yet cannot execute any commands without it; tools like Jan or Claude Desktop. With these agents, you can't even access remote APIs, making an MCP necessary despite its limitations.
A lot of providers already have native CLI tools with usually better auth support and longer sessions than MCP as well as more data in their training set on how to use those cli tools for many things. So why convert mcp->cli tool instead of using the existing cli tools in the first place? Using the atlassian MCP is dog shit for example, but using acli is great. Same for github, aws, etc.
You just reinvented Skills
Cheaper, but is it more effective?
I know I saw something about the Next.js devs experimenting with just dumping an entire index of doc files into AGENTS.md and it being used significantly more by Claude than any skills/tool call stuff.
At this stage would be much, much better to implement a RAG system based on semantic tool understanding. So that the relevant tools would pop up at every request and not bloat the context. And semantic search is just similarity search which is super fast.
clihub link is broken
A very good example of this is playwright-cli vs Playwright MCP: https://github.com/microsoft/playwright-cli
The biggest difference is state, but that's also kind of easy from CLI, the tool just have to store it on disk, not in process memory.
I had deepseek explain MCP to me. Then I asked what was the point of persistent connections and it said it was pretty much hipster bullshit and that some url to post to is really enough for an llm to interact with things.
I've seen folks say that the future of using computers will be with an LLM that generates code on the fly to accomplish tasks. I think this is a bit ridiculous, but I do think that operating computers through natural language instructions is superior for a lot of cases and that seems to be where we are headed.
I can see a future where software is built with a CLI interface underneath the (optional) GUI, letting an LLM hook directly into the underlying "business" logic to drive the application. Since LLM's are basically text machines, we just need somebody to invent a text-driven interface for them to use...oh wait!
Imagine booking a flight - the LLM connects to whatever booking software, pulls a list of commands, issues commands to the software, and then displays the output to the user in some fashion. It's basically just one big language translation task, something an LLM is best at, but you still have the guardrails of the CLI tool itself instead of having the LLM generate arbitrary code.
Another benefit is that the CLI output is introspectable. You can trace everything the LLM is doing if you want, as well as validate its commands if necessary (I want to check before it uses my credit card). You don't get this if it's generating a python script to hit some API.
Even before LLM's developers have been writing GUI applications as basically a CLI + GUI for testability, separation of concerns etc. Hopefully that will become more common.
Also this article was obviously AI generated. I'm not going to share my feelings about that.
[dead]
[dead]
[dead]
[dead]
[dead]
The article's link to clihub.sh is broken. Looks like https://clihub.org/ is the correct link? I've added that to the toptext as well.
Edit: took out because I think that was something different.
[dead]
There is some important context missing from the article.
First, MCP tools are sent on every request. If you look at the notion MCP the search tool description is basically a mini tutorial. This is going right into the context window. Given that in most cases MCP tool loading is all or nothing (unless you pre-select the tools by some other means) MCP in general will bloat your context significantly. I think I counted about 20 tools in GitHub Copilot VSCode extension recently. That's a lot!
Second, MCP tools are not compossible. When I call the notion search tool I get a dump of whatever they decide to return which might be a lot. The model has no means to decide how much data to process. You normally get a JSON data dump with many token-unfriendly data-points like identifiers, urls, etc. The CLI-based approach on the other hand is scriptable. Coding assistant will typically pipe the tool in jq or tail to process the data chunk by chunk because this is how they are trained these days.
If you want to use MCP in your agent, you need to bring in the MCP model and all of its baggage which is a lot. You need to handle oauth, handle tool loading and selection, reloading, etc.
The simpler solution is to have a single MCP server handling all of the things at system level and then have a tiny CLI that can call into the tools.
In the case of mcpshim (which I posted in another comment) the CLI communicates with the sever via a very simple unix socket using simple json. In fact, it is so simple that you can create a bash client in 5 lines of code.
This method is practically universal because most AI agents these days know how to use SKILLs. So the goal is to have more CLI tools. But instead of writing CLI for every service you can simply pivot on top of their existing MCP.
This solves the context problem in a very elegant way in my opinion.