## Kick Documentation

For the complete documentation index, see [llms.txt](https://docs.kick.co/llms.txt). This page is also available as [Markdown](https://docs.kick.co/ai/readme.md).

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.

## GitBook Assistant

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

### GitBook Assistant

- **MCP**  
- **CLI**

### How to use

#### GitBook Assistant

Your commonly used AI tools: Claude, ChatGPT, Gemini, Copilot, and more

#### Terminal

### What it is

- Connect an AI assistant (Claude, ChatGPT) and ask questions about client data in plain language
- Run terminal commands and scripts that pull data, check balances, and automate repeatable tasks

### Best for

- **GitBook Assistant**  
  - Exploratory work, drafting client messages, investigating issues  
- **CLI**  
  - Repeatable checks, bulk exports, scheduled month-end automation

### Use when

- **GitBook Assistant**  
  - The task is different every time and you want to ask follow-up questions  
- **CLI**  
  - You want to run the same check every month or hand a command to your team

### Example

- **GitBook Assistant**  
  - "Show me Acme's uncategorized transactions from the last 90 days"  
- **CLI**  
  - `kick --workspace acme reports trial-balance`

### Where to start

- [MCP Quickstart](https://docs.kick.co/ai/mcp/mcp-quickstart)  
- [CLI Quickstart](https://docs.kick.co/ai/cli/cli-quickstart)

Read more about [permissions and security](https://docs.kick.co/ai/permissions-and-security) when using AI with Kick or other tools.

Last updated 18 days ago.