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

# Zeplin Connector

<Badge icon="arrow-left" color="gray">[Back to Search AI connectors list](/ai-for-service/searchai/content-sources#supported-connectors)</Badge>

Zeplin is a collaboration tool for designers and developers that provides UI design handoffs with specs, assets, and code snippets. Search AI supports searching through **Screens** in connected Zeplin accounts.

| Specification              | Details |
| -------------------------- | ------- |
| Repository type            | Cloud   |
| Supported content          | Screens |
| RACL support               | Yes     |
| Content filtering          | No      |
| Auto permission resolution | Yes     |

## Connector Configuration

Search AI interacts with Zeplin via APIs. You can authenticate using either of the following methods:

* **Personal Access Token** — generate a token directly in your Zeplin profile
* **OAuth 2.0** — create an OAuth app in Zeplin and use the app credentials

## Prerequisites

### Generate a Personal Access Token

1. Go to your **Profile** page in Zeplin.
2. Navigate to the [Developer page](https://app.zeplin.io/profile/developer).
3. Under **Personal access tokens**, select **Create new token**.
4. Enter a name for the token.
5. Select **Enable admin access**.
6. Select **CREATE**. The access token is generated.
7. Copy the token — it will not be visible after you leave the page.

### Create an OAuth App in Zeplin

1. Go to your **Profile** page in Zeplin.
2. Navigate to the [Developer page](https://app.zeplin.io/profile/developer).
3. Under **Owned Zeplin apps**, select **Create new app**.
4. Provide the following details:
   * **Name** — unique, identifiable name for the app
   * **Summary** — brief description of the app's purpose
   * **Website** — your website URL
   * **Redirect URIs** — use one of the following based on your region or deployment:
     * JP Region: `https://jp-bots-idp.kore.ai/workflows/callback`
     * DE Region: `https://de-bots-idp.kore.ai/workflows/callback`
     * Production: `https://idp.kore.com/workflows/callback`
5. Select **CREATE**. A client ID and client secret are generated. Use these when configuring the connector in Search AI.

## Configure the Zeplin Connector in Search AI

On the **Authorization** tab of the connector, provide the following details.

| Field                  | Description                         |
| ---------------------- | ----------------------------------- |
| **Name**               | Unique name for the connector       |
| **Authorization Type** | Select **API Key** or **OAuth 2.0** |

**When using API Key authentication:**

| Field       | Description                               |
| ----------- | ----------------------------------------- |
| **API Key** | Personal access token generated in Zeplin |

**When using OAuth 2.0 authentication:**

| Field             | Description                                 |
| ----------------- | ------------------------------------------- |
| **Grant Type**    | Set to Authorization Code                   |
| **Client ID**     | Client ID generated in the Zeplin OAuth app |
| **Client Secret** | Client secret generated for the OAuth app   |

Click **Connect** to initiate authentication.

## Content Ingestion

After connecting the Zeplin account, go to the **Configuration** tab and select **Sync Now** to start ingestion. Use the **Scheduler** to set up a one-time or recurring sync.

Each screen is ingested as a separate document in Search AI with the following structure:

| Field        | Description                                                                         |
| ------------ | ----------------------------------------------------------------------------------- |
| **Title**    | Name of the screen                                                                  |
| **URL**      | Direct link to the screen in Zeplin                                                 |
| **Content**  | List of users with access and annotations (author, type, creation and update dates) |
| **Project**  | Name of the project containing the screen                                           |
| **Labels**   | Tags or labels applied to the screen                                                |
| **Comments** | All comments on the screen (author, text, creation and update dates)                |

## RACL Support

In Zeplin, access to screens is controlled at the project level. Anyone with access to a project automatically has access to all screens within that project.

When content is ingested into Search AI, the project ID is stored in the `sys_racl` field of the ingested chunks. These project IDs act as permission entities that control access.

Search AI supports automatic resolution of permission entities for Zeplin screens. It automatically identifies users with access to each project and associates them with the corresponding project ID permission entity — no manual API mapping is required.