Moderne Ai agent tool have have a setting where you can trimm down the numbers of tools from an MCP server. Usefull to avoid overwhelming the LLM with 80 tools description when you only need 1

▲

the_mitsuhiko 12 hours ago | parent | next [-]

I don't find that to help much at all, particularly because some tools really only make sense with a bunch of other tools and then your context is already polluted. It's surprisingly hard to do this right, unless you have a single tool MCP (eg: a code/eval based tool, or an inference based tool).

▲

stavros 12 hours ago | parent [-]

Don't you have a post about writing Python instead of using MCP? I can't see how MCP is more efficient than giving the LLM a bunch of function signatures and allow it to call them, but maybe I'm not familiar enough with MCP.

▲

the_mitsuhiko 12 hours ago | parent [-]

> Don't you have a post about writing Python instead of using MCP?

Yes, and that works really well. I also tried various attempts of letting agents to write code that exposes MCP tool calls via an in-language API. But it's just really, really hard to work with because MCP tools are generally not in the training set, but normal APIs are.

	▲	stavros 12 hours ago \| parent [-]
		Yeah, I've always thought that your proposal was much better. I don't know why one of the big companies hasn't released something that standardised on tool-calling via code, hm.

▲

incoming1211 10 hours ago | parent | prev [-]

Remote MCP with API key which has claims works well to reduce the tool count to only that of what you need.