Apideck CLI – An AI-agent interface with much lower context consumption than MCP
1–10 of 149 posts
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#2We built a unified API with a large surface area and ran into a problem when building our MCP server: tool definitions alone burned 50,000+ tokens before the agent touched a single user message.
The fix that worked for us was giving agents a CLI instead. ~80 tokens in the system prompt, progressive discovery through --help, and permission enforcement baked into the binary rather than prompts.
The post covers the benchmarks (Scalekit's 75-run comparison showed 4-32x token overhead for MCP vs CLI), the architecture, and an honest section on where CLIs fall short (streaming, delegated auth, distribution).
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#310 years from now: "Can you believe they did anything with such a small context window?"
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#4Graphql introspection queries would be a really neat application for LLM calls
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#510 years from now: "Can you believe they did anything with such a small context window?"
10 years from now: “what’s a context window?”
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#6What 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...
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#7> Not a protocol error, not a bad tool call. The connection never completed.
Very interesting topic, but this LLM structure is instant anthema I just have to stop reading once I smell it.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#8We built a unified API with a large surface area and ran into a problem when building our MCP server: tool definitions alone burned 50,000+ tokens before the agent touched a single user message. The fix that worked for us was giving agents a CLI instead. ~80 tokens in the system prompt, progressive discovery through --help, and permission enforcement baked into the binary rather than prompts. The post covers the benc…
How is progressive discovery not more expensive due to the increased number of steps?
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#9What 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...
You don't need a whole server to tell agents that, I think you can just write a skill file or two and be done with it.
Re: Apideck CLI – An AI-agent interface with much lower context consumption than MCP
#1010 years from now: "Can you believe they did anything with such a small context window?"
10 years from now: “what’s a context window?”
10 years from now: “come with me if you want to live”
Terminator 2 Clip: https://youtu.be/XTzTkRU6mRY?t=72&si=dmfLNDqpDZosSP4M