> ## 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 Cursor

> Register the Orca MCP server in Cursor and drive cloud agents from the editor.

Cursor 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 `.cursor/mcp.json` (project) or `~/.cursor/mcp.json` (global):

```json theme={null}
{
  "mcpServers": {
    "orca": {
      "command": "orca",
      "args": ["mcp", "serve"]
    }
  }
}
```

## What the agent gets

Nineteen curated tools covering the golden paths (create and run agents, follow runs with `wait_for_run`, skills, storage, publishing, usage) plus `api_request`, a raw authenticated escape hatch to every `/api/*` operation, self-documented by the `orca://openapi` resource.

## Headless login inside Cursor

`orca login` detects agent contexts (including Cursor) and uses the device flow automatically: it prints a one-time code and a URL to approve on any device, then stores the key itself. For scripted setups, export `ORCA_API_KEY` instead; details in [Headless authentication](/agents/headless-auth).