Skip to main content
Kibo documentation is designed to be AI-native, providing built-in tools to help you find answers faster and standard formats to integrate these docs into your own AI workflows.

​
Documentation Assistant

The integrated AI Assistant allows you to ask natural language questions about Kibo features, APIs, and guides.

​
How to use it

You can access the assistant in several ways:
  • “Ask AI” Button: Click the Ask AI button located in the search bar or navigation menu.
  • Keyboard Shortcut: Press Cmd + I (macOS) or Ctrl + I (Windows) to open the chat panel instantly.
  • Contextual Help: Highlight any text on a page and click Ask AI to get an explanation or clarification on that specific section.
The assistant cites its sources, allowing you to click through to the specific documentation page to verify information or read more.

​
Integration with External LLMs

If you use AI coding tools (such as Cursor, Windsurf, or GitHub Copilot) or chat with models like ChatGPT and Claude, you can provide this documentation as context to get accurate, up-to-date answers about Kibo. This site hosts standard text files optimized for Large Language Models (LLMs) to read and index.

​
Available Context Files

You can append the following paths to the root URL of this documentation site:
File PathDescriptionUse Case
/llms.txtA condensed map of the documentation site, including page titles and descriptions.Best for giving an AI an overview of what topics are available without overloading its context window.
/llms-full.txtA single file containing the full text of the entire documentation site.Best for “indexing” the docs in tools like Cursor or asking deep technical questions where the AI needs full details.

​
Example Usage

In Cursor or Windsurf: Add the documentation URL followed by /llms-full.txt to your @docs or knowledge base configuration. This allows the editor to understand Kibo SDKs and APIs while you write code. In ChatGPT or Claude: You can prompt the model:
“Read the documentation structure at https://docs.kibocommerce.com/llms.txt and tell me which section I should look at for [Your Topic].”

​
MCP Server

This documentation site includes a built-in Model Context Protocol (MCP) server that AI tools can connect to directly. This enables real-time access to the documentation without needing to manually copy or index files. Server URL: 
https://docs.kibocommerce.com/mcp
In Claude Desktop: Add the following to your claude_desktop_config.json file: 
{
  "mcpServers": {
    "kibo-docs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://docs.kibocommerce.com/mcp"
      ]
    }
  }
}
In Cursor: Add the MCP server in your Cursor settings under MCP Servers, or add it to your .cursor/mcp.json file: 
{
  "mcpServers": {
    "kibo-docs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://docs.kibocommerce.com/mcp"
      ]
    }
  }
}
In Windsurf: Add the following to your ~/.codeium/windsurf/mcp_config.json file: 
{
  "mcpServers": {
    "kibo-docs": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://docs.kibocommerce.com/mcp"
      ]
    }
  }
}
In VS Code with GitHub Copilot: Add the following to your VS Code settings.json file: 
{
  "mcp": {
    "servers": {
      "kibo-docs": {
        "command": "npx",
        "args": [
          "mcp-remote",
          "https://docs.kibocommerce.com/mcp"
        ]
      }
    }
  }
}
In Claude Code (CLI): Run the following command to add the MCP server: 
claude mcp add kibo-docs -- npx mcp-remote https://docs.kibocommerce.com/mcp
In ChatGPT (Developer Mode): ChatGPT supports remote MCP servers through Developer Mode. To connect:
  1. Go to Settings > Connectors > Advanced
  2. Enable Developer Mode
  3. In the Connectors tab, click Create
  4. Enter the server URL: https://docs.kibocommerce.com/mcp
  5. Save the connector
Once configured, the AI will have direct access to search and retrieve Kibo documentation as needed during your conversations.