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

# ChatGPT

> Connect ChatGPT to your data in Nekt using the MCP Server with OAuth authentication.

ChatGPT can query and analyze your data when connected to Nekt through the MCP Server. The connection uses OAuth, so you authenticate with your Nekt credentials directly — no manual token management required.

<Info>Requires a **paid Nekt plan** (for MCP Server access) and a **ChatGPT Plus, Team, or Enterprise** subscription (for MCP support).</Info>

## 1. Activate your MCP Server

The connection is made by activating the MCP Server in your workspace. Check [this guide](/mcp-server/setup) for instructions.

## 2. Connect ChatGPT to Nekt

<Steps>
  <Step title="Open the MCP connector settings in ChatGPT">
    In ChatGPT, click the **Tools** icon (wrench) in the prompt box, then select **Add MCP connector**.
  </Step>

  <Step title="Enter the connection details">
    You'll find the required values in the **Connection fields** section of the MCP Server page inside Nekt (**Integrations > MCP Server**).

    Fill in the following fields:

    1. **URL**: paste the value of the `Endpoint` field from Nekt
    2. **OAuth Client ID**: paste the `OAuth Client ID` value
    3. **OAuth Client Secret**: paste the `OAuth Client Secret` value

    Click **Add**.
  </Step>

  <Step title="Authenticate with Nekt">
    ChatGPT will redirect you to the Nekt login page. Sign in with your Nekt credentials.

    After authenticating, a list of your MCP tokens will be displayed.
  </Step>

  <Step title="Select your token">
    Tokens authenticate your requests to Nekt. They give ChatGPT access to the tables associated with each token.

    * If you haven't created any custom tokens yet, you'll see a default one created automatically with Full Access. This token accesses all tables in your workspace.
    * If you already have custom tokens, select the one you want to use.

    Click **Select Token** to confirm.

    <Note>
      Tokens created during the OAuth flow use the creating user's permissions by
      default. Tokens created manually can be scoped to specific tables for
      fine-grained access control.
    </Note>
  </Step>

  <Step title="Approve the MCP tools">
    Nekt MCP Server provides nine tools that AI agents can use to interact with your data. You can learn more about them [here](/mcp-server/tools).

    When ChatGPT prompts you to approve the Nekt tools, confirm to allow access.
  </Step>
</Steps>

***

## 3. Explore your data

Once connected, ask ChatGPT a question about your data. For example:

```
Give me a summary of the your_table_name table from Nekt.
```

ChatGPT will use the MCP tools to query your data and return an answer. You can see which tools were called and the queries executed in the response.

<Check>
  We'd love to know what you're building with Nekt! Share your projects with us through any of our communication channels.
</Check>

***

## Privacy & Security

Your data privacy is a core principle of the Nekt platform.

When you connect ChatGPT to Nekt through the MCP Server, ChatGPT does not receive direct database credentials or unrestricted access to your infrastructure. Instead, ChatGPT interacts with your data exclusively through the secure tools exposed by the Nekt MCP Server, which act as a controlled gateway to the Nekt API. These tools enforce the same authentication, authorization, and permission rules used throughout the Nekt platform.

Access is scoped using tokens and user permissions, meaning ChatGPT can only access the tables and actions explicitly allowed by the token you selected during connection. This architecture ensures that all queries, analysis, and data interactions remain governed, auditable, and restricted to your workspace permissions.

When using ChatGPT, your interactions are subject to OpenAI's privacy settings and policies. OpenAI allows users to control whether their conversations may be used for model training through their Data Controls settings.

We recommend reviewing the [official OpenAI privacy documentation](https://openai.com/policies/privacy-policy) to understand their data handling policies and selecting the configuration that best aligns with your organization's security requirements.

***

## Need help?

Contact our support team if you encounter issues during setup.