I am kind of confused why can't you just create a new MCP tool that encapsulates... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		arjunchint 6 months ago \| parent \| context \| favorite \| on: LLM function calls don't scale; code orchestration... I am kind of confused why can't you just create a new MCP tool that encapsulates parsing and other required steps together in a code block? This would be more reliable than expecting the LLM to generate working code 100% of the time?

Centigonal 6 months ago [–]

You should for sure do this for common post processing tasks. However, you're usually not going to know all the types of post-processing users will want to do with tool call output at design-time.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact