# Getting Started

Kick is built with AI at its core, powering how transactions are categorized, reviewed, and closed. Connect MCP or CLI to take it further: query your client data in plain language, automate month-end checks, and build workflows that run across every workspace.

Both connect directly to Kick. The difference is how you interact with your data:

<table><thead><tr><th width="100"></th><th>MCP</th><th>CLI</th></tr></thead><tbody><tr><td><strong>How to use</strong></td><td>Your commonly-used AI tools: Claude, ChatGPT, Gemini, Copilot, and more</td><td>Terminal</td></tr><tr><td><strong>What it is</strong></td><td>Connect an AI assistant (Claude, ChatGPT) and ask questions about client data in plain language</td><td>Run terminal commands and scripts that pull data, check balances, and automate repeatable tasks</td></tr><tr><td><strong>Best for</strong></td><td>Exploratory work, drafting client messages, investigating issues</td><td>Repeatable checks, bulk exports, scheduled month-end automation</td></tr><tr><td><strong>Use when</strong></td><td>The task is different every time and you want to ask follow-up questions</td><td>You want to run the same check every month or hand a command to your team</td></tr><tr><td><strong>Example</strong></td><td>"Show me Acme's uncategorized transactions from the last 90 days"</td><td><code>kick --workspace acme reports trial-balance</code></td></tr><tr><td><strong>Where to start</strong></td><td><a href="/pages/AZXXSQf8bPmEsmDNSwFh">MCP Quickstart</a></td><td><a href="/pages/aUzBS9MmBz9mhiLICPpK">CLI Quickstart</a></td></tr></tbody></table>

Read more about [permissions and security](/ai/permissions-and-security.md) using AI with Kick or other tools.\ <br>


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.kick.co/ai/getting-started.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.