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

# Get started with AI

<Note>The Stigg AI Terminal is currently in **public beta**. Feedback and bug reports are welcome.</Note>

Connect Stigg to your AI coding assistant in one command. The Stigg **AI Terminal** signs you in, sets up the [MCP server](/api-and-sdks/mcp-server), and installs the [agent skills](/api-and-sdks/agent-skills), so you can build pricing, entitlements, and usage tracking just by describing what you want.

```bash theme={null}
npx @stigg/terminal
```

That's it. The Terminal walks you through sign-in and detects the AI clients you have installed: Claude Code, Cursor, VS Code, Codex, or Claude Desktop. Don't have a Stigg account yet? [Create one free](https://app.stigg.io/signup).

***

## What it sets up

<Steps>
  <Step title="Signs you in">
    Authenticates to your Stigg account in the browser and lets you pick the environment to connect.
  </Step>

  <Step title="Connects the MCP server">
    Writes the Stigg [MCP server](/api-and-sdks/mcp-server) into each client's config, so your agent can act on your environment: create plans, provision customers, check entitlements, and report usage.
  </Step>

  <Step title="Installs the agent skills">
    Adds the Stigg [agent skills](/api-and-sdks/agent-skills): domain knowledge that teaches your assistant Stigg's pricing model, entitlement patterns, and best practices.
  </Step>
</Steps>

Restart your AI client when setup finishes, and you're ready to go. When you run the Terminal interactively, it can even launch your coding agent for you on success, seeded with a starter prompt so you can dive straight in.

***

## Try it

Once connected, describe what you want in natural language:

> *"Create a three-tier SaaS pricing model: Free with 1,000 API calls/month, Pro with 50,000 and overages, and Enterprise unlimited."*

> *"Add entitlement checks to our codebase: Pro users get 500 AI completions per month; show a paywall when they hit the limit."*

> *"Set up credits so users buy packs of 1,000 and each AI generation costs 10 credits."*

> *"Provision a 14-day Pro trial for customer acme-corp."*

The agent skills tell your assistant how Stigg works; the MCP server lets it make the changes in your environment.

<Note>
  Your agent acts on the environment you connect. Use a **sandbox** environment while you explore, and see the [security guidance](/api-and-sdks/mcp-server#security) before connecting production.
</Note>

***

## How it works

The AI Terminal automates the setup you'd otherwise do by hand. It detects your installed AI clients, signs you in, writes the MCP server config for each one, and installs the skills plugin, then your agent does the rest.

<Tip>
  Already inside an AI coding assistant? Ask it to set itself up: *"Connect this project to Stigg: run `npx @stigg/terminal init --headless` to install the MCP server and skills, then list my Stigg plans to confirm it worked."* It detects which client it's running in and configures it. CI pipelines can use the same headless mode; see the [AI Terminal reference](/api-and-sdks/ai-terminal#headless-usage).
</Tip>

***

## Learn more

<CardGroup cols={2}>
  <Card title="AI Terminal" icon="rocket" href="/api-and-sdks/ai-terminal">
    Full command reference, every flag, and headless / CI usage.
  </Card>

  <Card title="MCP Server" icon="robot" href="/api-and-sdks/mcp-server">
    What your agent connects to, and how to set it up manually.
  </Card>

  <Card title="Agent Skills" icon="wand-magic-sparkles" href="/api-and-sdks/agent-skills">
    The Stigg expertise the Terminal installs into your assistant.
  </Card>

  <Card title="CLI" icon="terminal" href="/api-and-sdks/cli">
    Prefer a scriptable REST wrapper? Use Stigg from the terminal.
  </Card>
</CardGroup>