10 years from now: "Can you believe they did anything with such a small context window?"
More likely: "Can you believe they were actually trying to use LLMs for this?"
Apideck CLI – An AI-agent interface with much lower context consumption than MCP
21–30 of 149 posts
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#22I'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 different servers.
MCP gives us a registry such that we can enforce MCP chain policies, i.e. no doing web search after viewing financials.
Doing the same with skills is not possible in a programatic and deterministic way.
There needs to be a middle ground instead of throwing out MCP entirely.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#23At this point, I feel like MCP servers are just not feasible at the current level of context windows and LLMs. Good idea, but we're way too early.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#24What I've done with my MCPs is turning them into a CLI, except there's still an MCP server that only has the instructions to tell the the agent about the CLI.[1] Claude and GLM-5 seem to have no problems with it. As a bonus, the entire thing now works as a plain old CLI too - which it honestly should have from the beginning. [1]: https://github.com/jcdickinson/ferrisfetch/blob/main/cmd/mcp...
Can the MCP tell them how to use the CLI? Surely that would mean less time wasted on discovering it each time. Going to try this with fastmail-cli and see what happens.
Yes, MCP instructions are a blob that is injected at the start of the context. That file is prefixed to the agent specific help[1] for the instructions (that is returned if --help is invoked with CLAUDE=1 or AGENT=1).
[1]: https://github.com/jcdickinson/ferrisfetch/blob/main/cmd/age...
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#25Why not use skills? They follow a three-tier loading approach, and you can stick an MCP as part of the toolset for the skills, so it will only load it when the skill is selected. See the progressive disclosure section in the skills docs: https://agentskills.io/what-are-skills
Three tiers? I thought it was two?
Discovery, Activation, Execution as per the linked doc
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#26Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#2710 years from now: "Can you believe they did anything with such a small context window?"
I am kind of already at that point. For all the complaining about context windows being stuffed with MCPs, I am curious what they are up to and how many MCPs they have that this is a problem.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#28There's already an open source tool that does exactly the same thing: https://github.com/knowsuchagency/mcp2cli
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#2910 years from now: "Can you believe they did anything with such a small context window?"
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"
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#30I'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…
MCPs are handy in their place. Agents calling CLI locally is much more efficient.