> For the complete documentation index, see [llms.txt](https://gitbook.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gitbook.com/docs/getting-started/llm-ready-docs.md).

# LLM-ready docs

Make your published docs easier for AI tools to discover, read, and use

GitBook automatically publishes AI-friendly formats for your docs site.

They help large language models (LLMs), coding agents, and AI search systems. These tools can discover and retrieve accurate documentation without parsing HTML.

## Markdown pages

Append `.md` to any published page URL to view its Markdown. Markdown gives AI tools structured content without the surrounding HTML.

<a href="https://gitbook.com/docs/publishing-documentation/llm-ready-docs.md" class="button primary">Check out the .md file for this page</a>

## llms.txt

[llms.txt](https://llmstxt.org/) is a proposed standard for LLM-friendly web content. Append `/llms.txt` to your docs site's root URL.

It lists every published page with a Markdown version. AI tools can use this index to discover your documentation.

<a href="https://gitbook.com/docs/llms.txt" class="button primary">Check out the /llms.txt for the GitBook docs</a>

## llms-full.txt

Append `/llms-full.txt` to your docs site's root URL. This file includes your full documentation content in one place.

Hidden pages are included in `llms-full.txt`. Hiding a page only removes it from the published table of contents.

<a href="https://gitbook.com/docs/llms-full.txt" class="button primary">Check out the /llms-full.txt file for the GitBook docs</a>

## MCP server for published docs

GitBook exposes a Model Context Protocol (MCP) server for every published docs site. Compatible tools can discover and retrieve your docs as structured resources.

Hidden pages remain available through the site’s MCP server. Hiding a page only removes it from the published table of contents.

Append `/~gitbook/mcp` to your docs site's root URL. For example, GitBook's MCP server is `https://gitbook.com/docs/~gitbook/mcp`.

{% hint style="info" %}
Opening this URL in a browser returns an error. Use a tool that can make HTTP requests.
{% endhint %}

Learn more in [MCP servers for published docs](/docs/ai-for-your-readers/mcp-servers-for-published-docs.md).

## Optimizing your docs for AI

GitBook handles the delivery layer. Your writing shapes the quality of AI answers.

Write content that AI tools can interpret reliably:

* Give each page a clear purpose.
* Use descriptive headings and short sections.
* State constraints, defaults, and requirements directly.
* Include concrete examples and exact values.
* Update content when your product changes.

These practices improve retrieval, reduce ambiguity, and help people find answers.

### Keeping translations aligned

If you publish in multiple languages, keep each translation aligned with its source.

[Translations](/docs/gitbook-agent/translations.md) let you localize content with GitBook Agent. When source content changes, GitBook can keep translated versions aligned.

### Measuring AI traffic

Use the [Agents & MCP](/docs/analytics/insights/agents-and-mcp.md) report in site analytics to track traffic from LLMs and MCP clients.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://gitbook.com/docs/getting-started/llm-ready-docs.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.