> **Building with AI coding agents?** Install the authstack plugin with one command. This equips your agent with accurate Scalekit implementation patterns.
>
> **Recommended** (the `-y` flags skip prompts, so the command runs without an interactive terminal):
> ```bash
> npx -y @scalekit-inc/cli setup -y
> ```
>
> Global:
> ```bash
> npm install -g @scalekit-inc/cli
> scalekit setup -y
> ```
>
> Supports Claude Code, Cursor, GitHub Copilot, Codex + skills for other Agent Skills-compatible agents in `~/.agents/skills`.
> Skills: integrate-agentkit, implement-saaskit, add-mcp-oauth, implement-sso, implement-scim.
> [Full setup guide](https://docs.scalekit.com/dev-kit/build-with-ai/)

---

# Agent Gateway quickstart

Enable Agent Gateway in the Scalekit dashboard, choose its connections, copy the MCP endpoint URL and connect your first AI client.
In this quickstart you enable Agent Gateway in one environment, check which connections it serves and connect your first AI client. It takes a few minutes, and everything happens in the Scalekit dashboard.

> note: Available on request
>
> Agent Gateway is available on request. [Contact us](/support/contact-us/) to enable it for your
> workspace.

## Before you start

- **Agent Gateway enabled for your workspace.** [Contact us](/support/contact-us/) if **Agent Gateway** isn't in the dashboard's product switcher.
- **At least one connection** in the environment, such as Gmail or Outlook. You can also add one during setup. [Set up connections](/agentkit/connections/) covers each connector's options.
- **An AI client that supports remote MCP servers**, such as Claude, ChatGPT, Cursor or VS Code.

1. ## Open Agent Gateway

   In the Scalekit dashboard, open the environment that has your connections. Then open the product switcher at the top of the left navigation and choose **Agent Gateway**.

   Select **Getting Started** to open **Get started with Gateway**.

2. ## Enable the Gateway

   Select **Enable Gateway**. Scalekit creates the Gateway's MCP endpoint for this environment and adds you as its first user.

3. ## Add users

   This step is optional. To give teammates access now, add each person's email address. They get access straight away, with no invitation email. You can add people later under **Identity**. Select **Next** to continue.

4. ## Check your connections

   **Add connections** lists the environment's connections. Check that the apps you want are there, then select **Next**.

   To add an app, select **Add connection** and follow the connector's setup. Agents can only use tools from connections listed here.

5. ## Copy the MCP endpoint URL

   **Your Gateway is ready** shows the **MCP endpoint URL**. Select **Copy URL**.

   Under **Connect your agent**, pick your AI client to see how to add the URL to it. Some clients, such as Cursor, open with a single click.

## Check it worked

1. Add the MCP endpoint URL to your AI client, as in [Connect AI clients](/agentkit/agent-gateway/connect-ai-clients/).
2. Sign in when the client opens the sign-in page, and approve the consent screen.
3. Ask the client to use one of your connections, for example "List my five most recent emails". If you haven't connected that app yet, the client gives you a link to connect it. Open it, sign in to the app and ask again.
4. In the dashboard, open **Logs**. The tool call appears there with its tool, connector and status.

## Next

- [Connect AI clients](/agentkit/agent-gateway/connect-ai-clients/): setup for Claude, ChatGPT, Cursor, VS Code, Claude Code, Windsurf and Grok Bot.
- [Users and access](/agentkit/agent-gateway/users-and-access/): add your team and sign them in with SSO.
- [Access policies](/agentkit/agent-gateway/access-policies/): choose which tools each group can use on each connection.


---

## More Scalekit documentation

| Resource | What it contains | When to use it |
|----------|-----------------|----------------|
| [/llms.txt](/llms.txt) | Structured index with routing hints per product area | Start here — find which documentation set covers your topic before loading full content |
| [/llms-full.txt](/llms-full.txt) | Complete documentation for all Scalekit products in one file | Use when you need exhaustive context across multiple products or when the topic spans several areas |
| [sitemap-0.xml](https://docs.scalekit.com/sitemap-0.xml) | Full URL list of every documentation page | Use to discover specific page URLs you can fetch for targeted, page-level answers |