> ## Documentation Index
> Fetch the complete documentation index at: https://docs.orcapods.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Use Orca from Codex

> Register the Orca MCP server in Codex CLI and drive cloud agents from it.

Codex CLI talks to Orca through the same MCP server the CLI ships.

## Setup

Install the CLI and sign in once:

```bash theme={null}
curl -fsSL https://orcapods.ai/install.sh | sh
orca login
```

Then register the server in `~/.codex/config.toml`:

```toml theme={null}
[mcp_servers.orca]
command = "orca"
args = ["mcp", "serve"]
```

## Notes

* The tool surface is identical across clients: golden-path tools plus the `api_request` escape hatch. See [The Orca MCP server](/agents/mcp) for the full table.
* In fully headless environments, skip the login flow and export `ORCA_API_KEY` before launching Codex; the server picks it up per call. See [Headless authentication](/agents/headless-auth).
* The `orca` CLI itself is also agent-friendly if you prefer shelling out: every command takes `--json`, streaming commands emit NDJSON, and exit codes are stable (0 ok, 1 failure, 2 usage, 3 auth, 4 not found).