LLM Integration

Nauthera publishes its documentation in machine-readable formats so that AI coding assistants can discover and reference it directly. This page explains how to set up your AI tools to use Nauthera docs as context.

#How It Works

Nauthera exposes two endpoints that follow the llms.txt standard:

For example:

• https://nauthera.io/llms.txt — full doc index
• https://nauthera.io/docs/next/installation.md — raw Installation Guide
• https://nauthera.io/docs/next/index.md — raw Introduction page

These endpoints return plain text (not HTML), making them ideal for LLM consumption.

#MCP Server

Nauthera provides a dedicated Model Context Protocol (MCP) server at https://nauthera.io/mcp. AI tools can connect directly to it — no third-party servers or Python dependencies required.

The MCP server exposes three tools:

#Claude Code

claude mcp add nauthera-docs --transport http https://nauthera.io/mcp

#Claude Desktop

Open Settings > Developer > Edit Config and add:

{
  "mcpServers": {
    "nauthera-docs": {
      "type": "streamable-http",
      "url": "https://nauthera.io/mcp"
    }
  }
}

Restart Claude Desktop.

#Cursor

In your project root, create or edit .cursor/mcp.json:

{
  "mcpServers": {
    "nauthera-docs": {
      "type": "streamable-http",
      "url": "https://nauthera.io/mcp"
    }
  }
}

#Windsurf

In your project root, create or edit .windsurf/mcp.json:

{
  "mcpServers": {
    "nauthera-docs": {
      "type": "streamable-http",
      "url": "https://nauthera.io/mcp"
    }
  }
}

#Direct URL Access

You can also fetch docs directly without MCP. Claude Code has built-in web fetching:

Fetch https://nauthera.io/llms.txt and summarize the available docs.

For persistent access, add doc URLs to your project's CLAUDE.md:

## Nauthera Docs
 
- Doc index: https://nauthera.io/llms.txt
- OidcClient CRD: https://nauthera.io/docs/next/oidc-client.md
- AuthPolicy CRD: https://nauthera.io/docs/next/auth-policy.md

#Available Docs

You can find the full list of available documentation pages at:

https://nauthera.io/llms.txt

Each entry includes the page title, URL, and a short description. All URLs ending in .md return raw markdown content.

#Next Steps

• Quick Start — Get Nauthera running in your cluster.
• Architecture — Understand Nauthera's operator model.