Developer argues MCP protocol is obsolete as LLMs improve
A technologist contends that LLMs now excel at direct API calls and CLI discovery, making the Model Context Protocol infrastructure unnecessary.
What to know
- A developer argues that MCP, created by Anthropic in 2024 as a bridge between LLMs and external services, is no longer necessary because modern models can call APIs, discover CLIs, and execute code directly.
- LLM capabilities have advanced faster than MCP infrastructure evolved; models can now write multi-service workflows and call unfamiliar APIs with minimal user intervention.
- The critique suggests a shift away from protocol-based agent abstraction toward direct model reasoning and terminal/sandbox execution as the primary pattern for external tool access.
maharshi365 Developer and criticAnthropic Original creator of MCPAgentic AI Foundation MCP governance body under Linux Foundation
How it unfolded 1 development · click the chart to see its coverage articlesposts
-
1
Maharshi365 describes architectural shift toward direct LLM capabilities
The developer explains that LLMs can now write scripts, compose multiple services, and call previously unseen APIs with minimal user intervention, and that platforms like Cloudflare's Code Mode exemplify moving MCP logic into model reasoning rather than protocol infrastructure.
“Agents with terminal access can replace most MCP servers and often are more capable.”
— maharshi365 -
I think many devs misunderstand MCP because they work in solo mode. In solo mode, you just have your secrets local. You don't care about auditing access. You don't have to account for different harnesses and tooling; you just use your own harness and adapt your tooling to it. You're not thinking about revoking/rotating secrets when someone leaves…
2 more of the top 3 · 71 posts in this stretch
-
H
Why MCP Was Always a Bad Idea L: https:// maharship.com/blog/why-mcp-was -always-a-bad-idea/ C: https:// news.ycombinator.com/item?id=4 9779329 posted on 2026.09.20 at 15:44:40 (c=0, p=5)
-
I have mixed feelings about this. Going all-in on Model Context Protocol (MCP) is definitely a bad idea because I noticed the Jira and GitLab MCPs were consuming an excessive amount of tokens. To solve this, I decided to install their respective CLIs instead so we could find a balance and get the best of both worlds. For example, certain MCPs…
-
-
background
Developer maharshi365 publishes critique of MCP as obsolete — In a detailed essay, the developer argues that modern LLMs have become capable enough to bypass MCP entirely through direct API calls, CLI discovery via --help commands, and code execution in sandboxed environments, making the protocol infrastructure unnecessary.
-
background
MCP donated to Agentic AI Foundation under Linux Foundation — Anthropic transferred stewardship of MCP to the newly formed Agentic AI Foundation as part of the Linux Foundation.
-
background
Anthropic releases Model Context Protocol — MCP launched as a protocol designed to help AI agents connect to external services and data sources at a time when LLMs were less capable.
Also covered reported alongside — the timeline has no entry for these yet
-
3 outlets Why MCP Was Always a Bad Idea
first by HN Frontpage, 5d ago · also Simon Willison, HN Best
1 more headline
- MCP was always a bad idea? Simon Willison · 5d ago
What people are saying 21 voices from 2 sites · best of 71 · verbatim
- Sep 22
-
Agree on flexibility, you can just do a lot more with AI agent + curl + SKILL.md.The agent comes with a good amount of API knowledge in training data already. A curated set of MCP tools throws most of that away. With curl, it can hit any endpoint and write scripts. SKILL.md covers what it gets wrong (API version, rate limits, etc.) and points at…
- Sep 21
-
MCP is like anything else.. it has its uses. Use it where it makes sense. Where it doesn't, don't. For my part, I probably rarely want my Agent to waste time writing its own adapter for a particular API that needs to be called, when I can just point it at an existing MCP server. And while context bloat can be a problem if you're using many many…
-
Article is focusing too much on tool use over HTTP. One of the good things about MCP is that it's the same protocol whether the tool is implemented with HTTP or using stdin over a local process. And it doesn't make sense to talk about HTTP headers with stdin.> There are still some issues, like CLIs returning machine-readable responses (JSON/XML…
-
I don't get excited about the directories listing all the MCPs that do all these random things. However, I used claude to create an MCP that is a gateway to our system and it's enabled some pretty helpful functionality for us. I use claude cowork to create email designs using data and content from our CMS, it can push accepted work straight into…
-
I think a most interesting middle ground option is the advent of CLIs specifically with agents in mind.For example, grafana has a newer CLI called gcx that replaced grafanactl https://grafana.com/docs/grafana/latest/as-code/observabilit...I originally used the MCP server but after running into context bloat and limitations around MCP I looked and…
-
I think there's at least one thing that MCPs get right, and it's that they make it easier to establish permission boundaries when agents are working with third part services and applications. Even with Claude from the terminal, MCP makes it easier for folks to standardize separate permissions and operations for general agent use than making people…
-
N
MCP was always a bad idea?: https:// maharship.com/blog/why-mcp-was -always-a-bad-idea/ Discussion: http:// news.ycombinator.com/item?id=4 9779329
-
The major advantage of CLI is IMHO that you can use a CLI yourself too. It's a universal tool.One thing I hate is when people write an MCP server for something useful and just that. Like, why don't you tell the same Claude or Codex instance you wrote to also expose the same functionalities as a CLI? The problem is that it's full of technical…
-
MCP is basically RPC, and it suffers all the problems of RPC like mechanisms. It has long round trips times, significant de/marshalling costs, coupling between caller and consumer, versioning issues, etc.Over time I think we'll see an evolution towards client-side micro models that reduces RTT latency, and a message bus architecture that allows…
-
> This article entirely misses the value that MCP brings today.Well, me too. I see the only advantage over a CLI app being an agreed-upon convention for syntax (not semantics).I have a CLI interface to my webapp, not an MCP.> If you want to operate something that's less YOLO than that, you'll find yourself wanting:> 1. Control over exactly which…
-
MCP definitely has its niche in certain environments. It's good for a specific kind of constrained problem; not so constrained that you could solve the problem with just Node.js + fetch call to LLM API but not so open that you'd want to let the AI agent directly invoke any service it wants over the web. The latter is what happens if you give the…
-
Correct me if I'm wrong, but an MCP server still make a lot of sense for remote-controlling a UI application (like a game engine editor) which otherwise doesn't have any 'access points' for remote-control right?An AmigaOS-style "scripting port" would work just as well, but AFAIK that's essentially what an MCP server is (a socket that implements a…
-
It is all useful, and depends on the distribution channel and surface complexity. I use both MCP and CLI in my case.Having the CLI allows you to have the huge application with the big surface be available to the AI agent and so they'll be able to learn it on demand. For example my app has more than 1,000 help pages. There are no other ways to load…
-
It would seem that curl + jq represents most of the solution these days. I recently learned that jq programs can be used in the other direction to effectively patch a json document too.Putting both of these things together, I am running out of problems to solve as a human developer in the space of AI agent integration.Assuming all your systems…
-
The title feels clickbaity. Direct API, CLI and MCP all have their uses.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. Also, a…
-
CLI, API, MCP are all useful ways to connect. It just depends on the use case you're going for. I've used all 3 and find that they all have benefits.MCPs are great when you just want that native out of the box low mistake way for agents to call your services it's great for certain cases.I also developed a new method of using MCP called ADP (Agent…
- Sep 20
-
Couldn't agree more. MCP is just Tool Use and the terminal agents all have embedded tool uses like WebSearch, Bash, Grep, etc and those are just MCP by another name. CLI's called by a model are just Bash Tool usage calls. Bash tool is just the most open ended broad MCP you can expose and what you gain is less context bloat (no specialized tool…
-
All of these things are perfectly possible with a plain REST API with an Open API spec and using some standard auth options, and an AI client that implements a reasonable “make api request tool” (just like the AI clients implement MCP today).I think the real value of MCP is that it allowed companies to say “we’re doing AI!” When they built an MCP…
-
I don't think MCP is a bad idea, but using them incorrectly is.CLI tools are great if you always use the same environment. But try using them from your iPhone, and they simply won't work; a remote MCP will work seamlessly.HTTP APIs solve a different problem. APIs are designed to be predictable and consistent, so the client always knows the…
-
This article entirely misses the value that MCP brings today.Sure, there's almost no reason to use MCPs if you are running a full-blown terminal agent (Claude Code, Codex, Meta Muse, OpenClaw etc) with unfettered internet access - just let it call APIs directly.If you want to operate something that's less YOLO than that, you'll find yourself…
-
This doesnt match my experience. Yesterday, I was using Microsoft's Power BI Authoring MCP to make a semantic model from some SQL or CSV files. It was magical.Microsoft has defined how to do that in the MCP. It's trivial to add the MCP to the machine and reliable in execution.The alternative would be the model having to get the documentation…