[dogman123]

Is there a way to have the model inside of codex to make use of chunkhound instead of its “built in” search/explore functionality with rg? Whenever I spin up a new agent using xhigh thinking it spins its wheels for a while to get up to speed — wondering if chunkhound can make this process faster.

[esafak]

That's what the MCP is for, if you can get the LLM to use it. Sometimes they just like to do it their own way :)

[strainer_spoon]

The ChunkHound docs are a bit confusing for making it available as an MCP server for Codex. How exactly do you do it? I got up to the indexing step and now need to let Codex be able to use it.