Hacker News new | ask | show | jobs
by zamalek 99 days ago
What 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...
2 comments
patates 99 days ago
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.
link
zamalek 99 days ago
That would work, and is still an option. However I think this makes deployment/installation simpler (which is also why I write my MCPs in go).
link
antihero 99 days ago
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.

link
zamalek 99 days ago
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...

link
antihero 98 days ago
Ah cool, that said: If your tool is primarily for Claude Desktop (or mobile if hosted), that surely needs the MCP to actually do anything right?
link
zamalek 98 days ago
I'm not sure about Claude Desktop (it must surely have CLI access?), but I think your line of thinking is correct.
link