Can a CAO agent answer a research question with real evidence, meaning a citation count for every paper and a publication date for every news claim, without you writing any code? Yes. It takes one agent profile with a six-line mcpServers entry that points at a remote MCP server and passes an API key in a header. CAO resolves the key from its managed environment at launch, the provider connects to the server, and the agent gets fourteen search tools it did not have before. This post shows the result first, then how the wiring works, then the parts that did not go smoothly.

I broke my own agent twice in one week. Once by hand, once with help from a very confident language model. This post is about both breaks, and about the Profiles tab in the CAO Web UI that turns machine-written profiles from "looks right" into "checked."

The reference documentation tells you what CAO does. It's a poor fit for the other half of the story — the walkthrough that takes an hour, the design decision that needs three diagrams to justify, the write-up of an orchestration that worked on real work and the two that didn't. This blog is where that goes.

Anyone who contributes to CLI Agent Orchestrator can publish here. Posts live in docusaurus/blog/ and ship through the same pull request review as the rest of the repository.