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

# Use these docs with AI tools

> Connect Claude, Cursor, VS Code, and other AI tools to the MacStadium docs MCP server, so answers come from the current documentation instead of a model's training data.

If you ask an AI assistant about Orka or MacStadium, it answers from what it learned in training, which can be out of date. For example, Orka 4.0 renamed the CLI from `orka3` to `orka`, and a model trained before that will still give you `orka3` commands. Connecting your assistant to these docs means it looks up the current pages before it answers.

## Connect the MacStadium docs MCP server

The docs have a [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server at:

```text theme={null}
https://docs.macstadium.com/mcp
```

It's public, and there's nothing to sign in to. Once it's connected, your assistant can search the docs, read full pages, and report a page that's wrong or missing information so we can fix it.

> [tab] Claude Code
>
> ```bash theme={null}
> claude mcp add --transport http macstadium-docs https://docs.macstadium.com/mcp
> ```
>
> Add `--scope user` to make it available in every project.

> [tab] Claude
>
> In Claude on the web or desktop, add `https://docs.macstadium.com/mcp` as a custom connector.

> [tab] Cursor and VS Code
>
> Open the menu at the top of any docs page and select **Connect to Cursor** or **Connect to VS Code**.

> [tab] Other tools
>
> Open the menu at the top of any docs page and select **Copy MCP server URL**, then add it to your tool as a remote (HTTP) MCP server.

## Use a single page

To work with one page instead of connecting the whole site, open the menu at the top of the page. You can copy the page as Markdown, or open it directly in Claude or ChatGPT with the page already attached.

## For tools that read llms.txt

The docs also publish:

* [`llms.txt`](https://docs.macstadium.com/llms.txt): an index of every page with a short description.
* [`llms-full.txt`](https://docs.macstadium.com/llms-full.txt): the full text of the docs in one file.

## Working with the Orka CLI

For help running Orka commands, pair the docs MCP server with the [Orka CLI agent skill](https://github.com/macstadium/orka3-cli-agent-skill). The skill gives your assistant Orka CLI syntax, workflows, and troubleshooting steps, and the MCP server gives it the current docs.


## Related topics

- [Orka macOS virtualization platform overview](https://docs.macstadium.com/orka/orka-overview/orka-overview.md)
- [Deploy your first VM with the Orka CLI](https://docs.macstadium.com/orka/quick-start-guides/orka-cli-quick-start.md)
- [AI agent integration with the Orka CLI](https://docs.macstadium.com/orka/orka-devops-integrations/claude-code.md)
- [Use Harbor OCI storage with the Orka CLI](https://docs.macstadium.com/orka/oci-images/using-harbor-oci-storage-with-the-orka-cli.md)
- [Common macOS CI/CD tools for MacStadium](https://docs.macstadium.com/iaas/bare-metal-macs/common-tools.md)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.