> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.knapsack.cloud/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.knapsack.cloud/_mcp/server.

# llms.txt

## Introduction

Alongside the [MCP server](/intelligent-tools/mcp-server), this documentation site publishes an [`llms.txt`](https://llmstxt.org/) file — a standard that lets AI tools discover and index a site without scraping rendered HTML. It's available at:

`https://docs.knapsack.cloud/llms.txt`

`llms.txt` is also scoped to any section of these docs, so an agent can request just the part it needs:

`https://docs.knapsack.cloud/intelligent-tools/llms.txt`

***

## What it contains

Each page is distilled into a title, a one-sentence description, and a URL:

```txt title="docs.knapsack.cloud/llms.txt (excerpt)"
- [Get Started](https://docs.knapsack.cloud/get-started): Set up your workspace, install Knapsack, and deploy it for your team.
- [Design Tokens and Variables](https://docs.knapsack.cloud/design-tokens): Manage the design tokens and variables that power your design system.
```

The description comes from each page's frontmatter `description` field, falling back to `subtitle` when no `description` is set.

***

## Reading a single page as Markdown

To fetch any page here as clean Markdown instead of HTML, append `.md` to its URL:

`https://docs.knapsack.cloud/get-started.md`

The **View as Markdown** and **Copy page** page-action buttons at the top of every page do the same thing without editing the URL by hand.

***

## When to use which

* Pointing an agent at the whole site, or one section of it: `llms.txt`.
* Pointing it at a single page, or copying a page for your own agent: the `.md` URL or the page-action buttons.
* Interactive, conversational access from an AI coding tool: the [MCP server](/intelligent-tools/mcp-server).