> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qwoty.io/llms.txt
> Use this file to discover all available pages before exploring further.

# Build with LLMs

> Use Qwoty documentation and APIs with AI assistants and LLMs.

You can use large language models (LLMs) to assist in building Qwoty integrations. This page explains how to access our documentation in LLM-friendly formats and how to connect AI assistants directly to your Qwoty account.

## Using documentation with LLMs

### llms.txt

The [llms.txt file](https://llmstxt.org) is an industry standard that helps LLMs index content efficiently, similar to how a sitemap helps search engines. AI tools use this file to understand your documentation structure and find relevant content.

We automatically host an `llms.txt` file that lists all available pages: [docs.qwoty.io/llms.txt](https://docs.qwoty.io/llms.txt)

### skill.md

The [skill.md specification](https://agentskills.io/specification) is a structured, machine-readable format that describes what AI agents can accomplish with Qwoty. While `llms.txt` tells agents where to find information, `skill.md` tells them what capabilities are available, what inputs are required, and what constraints apply.

We automatically host a `skill.md` file: [docs.qwoty.io/skill.md](https://docs.qwoty.io/skill.md)

Agents can process this file using the [skills CLI](https://www.npmjs.com/package/skills):

```bash theme={null}
npx skills add docs.qwoty.io/skill.md
```

### Documentation MCP Server

The [Model Context Protocol (MCP)](https://modelcontextprotocol.io) is an open standard that allows AI assistants to connect directly to external services. When connected to our documentation MCP server, AI tools can search our docs during response generation — providing more accurate answers than generic web searches.

Connect your AI tools to our documentation MCP server at `https://docs.qwoty.io/mcp`:

<Tabs>
  <Tab title="Claude">
    1. Navigate to the [Connectors](https://claude.ai/settings/connectors) page in the Claude settings
    2. Select **Add custom connector**
    3. Add the server name (e.g., `qwoty-docs`) and URL: `https://docs.qwoty.io/mcp`
    4. Select **Add**
    5. In a conversation, open the search and tools menu and select the **qwoty-docs** connector to activate it
  </Tab>

  <Tab title="Claude Code">
    Run the following command to add the Qwoty Docs MCP server:

    ```bash theme={null}
    claude mcp add --transport http qwoty-docs https://docs.qwoty.io/mcp
    ```
  </Tab>

  <Tab title="Cursor">
    1. Use `Command` + `Shift` + `P` (`Ctrl` + `Shift` + `P` on Windows) to open the command palette
    2. Search for "Open MCP settings"
    3. Select **Add custom MCP** to open the `mcp.json` file
    4. Configure the server:

    ```json theme={null}
    {
      "mcpServers": {
        "qwoty-docs": {
          "url": "https://docs.qwoty.io/mcp"
        }
      }
    }
    ```
  </Tab>

  <Tab title="VS Code">
    1. Create a `.vscode/mcp.json` file in your project
    2. Configure the server:

    ```json theme={null}
    {
      "servers": {
        "qwoty-docs": {
          "type": "http",
          "url": "https://docs.qwoty.io/mcp"
        }
      }
    }
    ```
  </Tab>
</Tabs>