Getting Started | AI & MCP | Kick Docs

Kick Documentation

For the complete documentation index, see llms.txt. This page is also available as Markdown.

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
• CLI Quickstart

Read more about permissions and security when using AI with Kick or other tools.

Last updated 18 days ago.