​
Introduction

Building with AI tools that have information and context about Auth for GenAI enables you to accelerate your development workflows. By providing these tools with the right information, you can get instant, context-aware answers and even delegate tasks to AI agents. This allows you to:
  • Ask questions in natural language to get up-to-date answers on how to set up and integrate with Auth for GenAI.
  • Generate accurate code snippets and get direct links to relevant documentation to help you implement changes faster.
  • Have AI agents read documentation to understand complex requirements and apply them to your codebase.

​
How it works

​
LLM context files

You can provide your AI with targeted information from raw text files (llms.txt), individual markdown pages, or URLs to help it perform a specific task. To enable your AI tools to index and search the documentation, use the following files:
  • For a high-level overview, the llms.txt file at https://auth0.com/ai/docs/llms.txt offers concise summaries of all our documentation pages.
  • If you need the complete content, you can use the llms-full.txt file at https://auth0.com/ai/docs/llms-full.txt, which contains the full content of our documentation in a single file.
  • Additionally, you can get a markdown version of any individual page. Click Copy page at the top of the page or append .md to any page URL.
We recommend using the Auth for GenAI MCP Server over context files to ensure your AI tools always have access to the most up-to-date information.

​
MCP servers

A more powerful method is connecting your tool to an MCP server. These servers act like a specialized API for your AI, allowing them to search for and read documents or perform actions on your behalf.

​
Auth0 MCP Server

The Auth0 MCP Server allows authenticated AI agents to perform actions in your Auth0 tenant, such as creating applications, configuring connections, and more. To learn how to connect your AI tool to the Auth0 MCP Server, read the Auth0 MCP Server documentation.

​
Auth for GenAI MCP Server

The Auth for GenAI MCP Server provides read-only access to our complete documentation. Use this server to ask questions and get context-aware answers about integrating with Auth for GenAI. This MCP server helps your AI tools implement the Auth for GenAI functionality. The Auth for GenAI MCP Server has the following endpoint metadata:
  • Server Name: Auth for GenAI
  • Server URL: https://auth0.com/ai/docs/mcp
  • Transport Type: HTTP
You can also connect your AI tool to the Auth for GenAI MCP Server by following one of our guides.
To automatically connect VS Code to the Auth for GenAI MCP Server, click the down arrow icon next to Copy page and select Connect to VS Code.
Or create a .vscode/mcp.json file and add:
{
  "servers": {
    "Auth for GenAI": {
      "type": "http",
      "url": "https://auth0.com/ai/docs/mcp"
    }
  }
}
To learn more, read the VS Code documentation.

​
How to use the Auth for GenAI Docs MCP server

After adding the MCP server to your AI tool, you can ask it questions about how to set up, configure, or integrate with Auth for GenAI. AI coding agents will be able to automatically retrieve the matching documentation for steps, references, and examples when applying code changes.

​
Sample prompts

Use these sample prompts to get a quick response, start building a new app, or integrate functionality into your existing app:
  • Use the Auth for GenAI MCP server to tell me about accessing 3rd party APIs using a user’s credentials.
  • Add a tool call to my AI agent that will access the user’s Google calendar and answer questions about their schedule and meetings. Use the Auth for GenAI MCP Server to find and follow the instructions on using Auth0 to securely call the Google API using the user’s credentials.
  • Build me a Next.js AI chatbot app that uses Langgraph to make tool calls to Google Calendar. Use Auth0 for user login and to secure the tool calls to the user’s calendar. Use the Auth for GenAI MCP Server for instructions.
Even with access to the most up-to-date documentation, AI tools can make mistakes. Always review AI-generated code for accuracy.