> For the complete documentation index, see [llms.txt](https://docs.dapta.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.dapta.ai/dapta-mcp/setup/connect-chatgpt.md).

# Connect ChatGPT

Connect the Dapta MCP to the ChatGPT desktop app with your Dapta account. Create an MCP app, sign in, install it and ask. No API key needed.

The ChatGPT desktop app connects to Dapta through an **MCP app** that you create once and sign in to with your Dapta account. There is no API key to copy and nothing to download. The same steps work in the Codex desktop app.

{% hint style="info" %}
Dapta is also on its way to ChatGPT's own list of apps. Once it is listed you will be able to add it from there. Until then, the steps below work today.
{% endhint %}

***

## Before you start

* The **ChatGPT desktop app**.
* A **Dapta account** that is an owner or admin of at least one workspace.

***

**Step 1:** In the ChatGPT desktop app, switch to **Work** mode. Open **Plugins**, click **Add** and choose **Create MCP App**.

***

**Step 2:** Fill in the form:

* **Name:** `Dapta`
* **Server URL:**

```
https://mcp.dapta.ai/mcp
```

* **Authentication:** leave it on **OAuth**.

ChatGPT shows a red warning for every custom app. Check **I understand and want to continue** and create the app.

***

**Step 3:** Click **Continue to Dapta**. Your browser opens Dapta's sign-in page: enter your Dapta email and the 6-digit code we email you, then click **Open ChatGPT** to come back.

***

**Step 4:** In **Plugins**, open the **Personal** tab, choose **Dapta** and click **Install plugin**. The browser opens once more to link your account: click **Open ChatGPT** again. That second sign-in is expected.

***

**Step 5:** Click **Try now**, type `@Dapta` and ask, for example:

> **List my agents**

If your account has several workspaces, ChatGPT lists them by name and asks which one to work in. Answer with the name. To change later, say "switch to \<workspace>". Every answer says which workspace it used.

***

{% hint style="success" %}
**Your data stays safe.** When ChatGPT changes something in Dapta, it shows you a preview first and waits for your confirmation. Reading information never needs confirmation. See [Privacy and data handling](/dapta-mcp/privacy.md) for what OpenAI receives when you use Dapta from ChatGPT.
{% endhint %}

{% content-ref url="/pages/y0N0ytQ0C9FIgnF9BZoY" %}
[Verify your connection](/dapta-mcp/setup/verify.md)
{% endcontent-ref %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.dapta.ai/dapta-mcp/setup/connect-chatgpt.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.