Comment by dools

5 days ago

Agents just do this anyway, how is it a “mode”? I always see the agent writing scripts in a tmp dir to execute or even just inlining bash and python scripts.

8 comments

dools

Reply
jsw97  4 days ago

Perhaps the appeal is a stronger and more customizable lockdown on agent capabilities.

  • imtringued  4 days ago

    We're in a HN submission about the least locked down LLM harness, it's too late for that.

    • agentdev001  4 days ago

      We're in an HN submission about the least locked down by default harness. Pi is aimed at being extended, openclaw is a good example of this. You can buy a box of razor blades and put them in any number of razors.

      1 reply →

Cilvic  4 days ago

but these bash scripts can not execute MCP tools.

What if I have an MCP Tool LookupZip(City) and want to chain it with a bash tool that prodcues a list of 100 cities. And then I want to filter again to the largest Zip code.

  • jsw97  4 days ago

    Yeah but arguably that tool should be a cli anyway, or could easily be converted to one. The benefit of MCP is that it's _less_ capable than bash.

    • agentdev001  4 days ago

      Not in my testing. A lot of the benefit comes from the tool definitions (from mcp) existing in the context window of the first turn. You could replicate this of course by describing your cli tool in the initial user/system prompt- but, mcp is already 'built' for this at the client (harness) level generally.