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

# Build with LLMs

> Use Hyperline documentation and APIs with AI assistants, LLMs, and agent frameworks through CLI, MCP server, and structured machine-readable docs.

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

Hyperline automatically hosts an `llms.txt` file that lists all available pages: [docs.hyperline.co/llms.txt](https://docs.hyperline.co/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 Hyperline. 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.

Hyperline automatically hosts a `skill.md` file: [docs.hyperline.co/skill.md](https://docs.hyperline.co/skill.md)

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

```bash theme={null}
npx skills add docs.hyperline.co/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 the Hyperline documentation MCP server, AI tools can search Hyperline docs during response generation. This provides more accurate answers than generic web searches.

Connect your AI tools to the documentation MCP server at `https://docs.hyperline.co/mcp`:

<Tabs>
  <Tab title="Claude">
    1. Go to the [Connectors](https://claude.ai/settings/connectors) page in the Claude settings
    2. Click **Add custom connector**
    3. Add the server name (e.g., `hyperline-docs`) and URL: `https://docs.hyperline.co/mcp`
    4. Click **Add**
    5. When using Claude, click the attachments button (the <kbd>+</kbd> icon)
    6. Select your MCP server
  </Tab>

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

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

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

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

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

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

## Hyperline MCP server

Beyond accessing documentation, you can connect AI assistants directly to your Hyperline account to **interact with your billing data** using natural language. The Hyperline MCP server enables you to:

* Query and manage customers
* View and create subscriptions
* Generate invoices
* Access analytics and revenue metrics
* And more

This allows you to ask your AI assistant questions like:

* "Show me all customers with overdue invoices"
* "What's my current MRR?"
* "Create a new subscription for customer X"

<Card title="Hyperline MCP server" icon="robot" href="./mcp">
  Learn how to set up and use the Hyperline MCP server to connect AI assistants to your billing data.
</Card>

## Hyperline CLI

For AI agents that work in the terminal (Claude Code, Cursor, Windsurf), the Hyperline CLI offers a lighter, faster alternative to MCP. Commands like `hyperline customers list` are token-efficient and require no tool discovery. This makes agents faster and more reliable on complex, multi-step tasks.

<Card title="Hyperline CLI" icon="terminal" href="./cli">
  Learn how to install and use the Hyperline CLI for agent-first billing operations.
</Card>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.