The trend is obviously towards larger and larger context windows. We moved from 200K to 1M tokens being standard just this year.
This might be a complete non issue in 6 months.
Apideck CLI – An AI-agent interface with much lower context consumption than MCP
41–50 of 149 posts
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#42I'm getting tired of everyone saying "MCP is dead, use CLIs!". Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills. The problem with tossing it out entirely is that it leaves a lot more questions for handling security. When using skills, there's no implicit way to be able to apply policies in the sane way across many…
Tool search pretty much completely negates the MCP context window argument.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#43I'm getting tired of everyone saying "MCP is dead, use CLIs!". Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills. The problem with tossing it out entirely is that it leaves a lot more questions for handling security. When using skills, there's no implicit way to be able to apply policies in the sane way across many…
Skills are just prompts, so policy doesn't apply there. MCP isn't giving you any special policy control there, it's just a capability border. You could do the same thing with a service mesh or any other capability compartmentalization technique.
The only value in MCP is that it's intended "for agents" and it has traction.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#44One of the MCP Core Maintainers here, so take this with a boulder of salt if you're skeptical of my biases.
The debate around "MCP vs. CLI" is somewhat pointless to me personally. Use whatever gets the job done. MCP is much more than just tool calling - it also happens to provide a set of consistent rails for an agent to follow. Besides, we as developers often forget that the things we build are also consumed by non-technical folks - I have no desire to teach my parents to install random CLIs to get things done instead of plugging a URI to a hosted MCP server with a well-defined impact radius. The entire security posture of "Install this CLI with access to everything on your box" terrifies me.
The context window argument is also an agent harness challenge more than anything else - modern MCP clients do smart tool search that obviates the entire "I am sending the full list of tools back and forth" mode of operation. At this point it's just a trope that is repeated from blog post to blog post. This blog post too alludes to this and talks about the need for infrastructure to make it work, but it just isn't the case. It's a pattern that's being adopted broadly as we speak.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#45The trend is obviously towards larger and larger context windows. We moved from 200K to 1M tokens being standard just this year. This might be a complete non issue in 6 months.
Context windows getting bigger doesn't make the economics go away. Tokens still cost money. 50K tokens of schemas at 1M context is the same dollar cost as 50K tokens at 200K context, you just have more room left over.
The pattern with every resource expansion is the same: usage scales to fill it. Bigger windows mean more integrations connected, not leaner ones. Progressive disclosure is cheaper at any window size.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#46Let me guess - another article about how CLI s are superior to MCP?
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#47I'm getting tired of everyone saying "MCP is dead, use CLIs!". Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills. The problem with tossing it out entirely is that it leaves a lot more questions for handling security. When using skills, there's no implicit way to be able to apply policies in the sane way across many…
> Yes, MCP eats up context windows, but agents can also be smarter about how they load the MCP context in the first place, using similar strategy to skills.
I have been keeping an eye on MCP context usage with Claude Code's /context command.
When I ran it a couple months ago, supabase used 13.2k tokens all the time, with the search_docs tool using 8k! So, I disabled that tool in my config.
I just ran /context now, and when not being used it uses only ~300 tokens.
I have a question. Does anyone know a good way to benchmark actual MCP context usage in Claude Code now? I just tried a few different things and none of them worked.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#48The industry is talking in circles here. All you need is "composability".
UNIX solved this with files and pipes for data, and processes for compute.
AI agents are solving this this with sub-agents for data, and "code execution" for compute.
The UNIX approach is both technically correct and elegant, and what I strongly favor too.
The agent + MCP approach is getting there. But not every harness has sub-agents, or their invocation is non-deterministic, which is where "MCP context bloat" happens.
Source: building an small business agent at https://housecat.com/.
We do have APIs wrapped in MCP. But we only give the agent BASH, an CLI wrapper for the MCPs, and the ability to write code, and works great.
"It's a UNIX system! I know this!"
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#49Earlier quoted context omitted.
10 years from now: "The next big thing: HENG - Human Engineers! These make mistakes, but when they do, they can just learn from it and move on and never make it again! It's like magic! Almost as smart as GPT-63.3-Fast-Xtra-Ultra-Google23-v2-Mem-Quantum"
Imagine believing humans don’t make the same mistakes. You live in a different universe than me buddy.
Sometimes we repeat mistakes. But humans are capable of occasionally learning. I've seen it!