# Quick Start

This guide gets you from zero to running your first ABsmartly command via the MCP server in under five minutes. We'll use **Claude Desktop** with **OAuth** — the fastest path with no API keys to manage.

For other clients or API key setups, jump straight to [Setup](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/setup.md).

## Prerequisites

* **Claude Desktop** installed ([download](https://claude.ai/download))
* An ABsmartly account on your instance (the URL you log into, e.g. `https://your-company.absmartly.com`)

## 1. Add the connector

In Claude Desktop, open **Settings → Connectors**, scroll to the bottom, and click **Add custom connector**.

![Claude Desktop Connectors settings](/assets/images/claude-desktop-connectors-cb70bec7a9a06104f61a845771027f95.png)

In the dialog:

* **Name:** `ABsmartly`
* **Remote MCP server URL:**

```text
https://mcp.absmartly.com/mcp?absmartly-endpoint=https://your-instance.absmartly.com
```

Replace `your-instance` with your ABsmartly subdomain.

![Add custom connector dialog](/assets/images/claude-desktop-add-custom-connector-b4eb77e1a251f0a69cfe7b02855a6d93.png)

Click **Add**, then **Connect**.

## 2. Sign in

Claude Desktop opens your browser. Review the **Authorize Access** page, which shows that Claude is asking for access to your ABsmartly account, and click **Approve**. Then sign in with your normal ABsmartly credentials (SAML/SSO if your org uses it). When the browser confirms success, the connector is live.

Your approval is remembered in that browser, so reconnecting later skips the consent page. See [OAuth & Client Registration](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/oauth-clients.md) for what happens behind the scenes.

> **tip**
>
> If you didn't include `absmartly-endpoint` in the URL, the OAuth flow prompts you for it in the browser before login.
>
> ![Connect to ABsmartly endpoint prompt](/assets/images/oauth-endpoint-prompt-ffbae2a41eac5b0caa6617fb0990388a.png)

## 3. Verify the connection

Back in Claude Desktop, start a new chat and try:

```text
Are we authenticated with ABsmartly?
```

The assistant calls `get_auth_status` and returns your email, name, instance endpoint and auth type (`OAuth`).

## 4. Run your first command

```text
Show me the experiments that are currently running on ABsmartly
```

Behind the scenes the assistant calls:

```text
execute_command(group: "experiments", command: "listExperiments",
                params: { state: "running" })
```

It returns the list, formatted for chat.

## 5. Try something useful

A few prompts that work out of the box (and don't change any state):

```text
List all metrics that are pending review
```

```text
Which teams own experiments that have been running for more than 14 days?
```

```text
Show me the goals defined for the "checkout" application
```

When you're ready to **create or change** something, the assistant will pause and show a preview / confirmation step — destructive actions like `start`, `stop`, `archive`, and `delete` always ask you to confirm before they run.

## Where to go next

* **[Usage Examples](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/usage-examples.md)** — more natural-language prompts that work today
* **[Tools Reference](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/tools-reference.md)** — the full set of commands, including experiment creation from markdown templates
* **[Authentication](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/authentication.md)** — switch to API key auth (for CI or headless use), or learn about the security model
* **[Troubleshooting](https://docs.absmartly.com/docs/APIs-and-SDKs/MCP-Server/troubleshooting.md)** — if the connection isn't working, start here
