> 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-claude-desktop.md).

# Connect claude.ai & Claude Desktop

Connect the Dapta MCP to claude.ai and Claude Desktop. Sign in with your Dapta account, or paste a connector URL that carries an API key. Nothing to download.

claude.ai (web and mobile), Claude Desktop and Cowork connect to Dapta through a **connector**. Signing in with your Dapta account is the recommended way. A connector URL with an API key also works when you want the connection fixed to one workspace.

{% hint style="info" %}
The old Claude Desktop plugin (`.zip`) is retired. If you installed it, remove it and connect with one of the options below.
{% endhint %}

***

## Option A: sign in with your Dapta account

### From the Claude connectors directory

Once Dapta is listed in the directory: open **Connectors**, find **Dapta**, click **Connect**, sign in with your Dapta account and approve the access.

{% content-ref url="/pages/nriNEe6uXqHeIL2IXLB5" %}
[Connect from the Claude connectors directory](/dapta-mcp/claude-connectors-directory.md)
{% endcontent-ref %}

### As a custom connector

This works today, with no directory needed.

**Step 1:** In claude.ai, Claude Desktop or Cowork, click **+** in the chat box, then **Connectors**, **Add connector** and **Add custom connector**. You can also get there from **Settings**, then **Connectors**.

***

**Step 2:** Name it **Dapta** and paste the server URL, with no key in it:

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

Leave the advanced settings (OAuth client ID and secret) empty and click **Add**.

***

**Step 3:** Your browser opens Dapta's sign-in page (`auth.dapta.ai`). Confirm, enter your Dapta email and type the 6-digit code we email you. Back in Claude, Dapta shows as **Connected**.

***

**Step 4:** Open a new chat and ask, for example, "List my agents in Dapta". If your account has one workspace, Claude uses it. If it has several, Claude lists them by name and asks which one to work in. Answer with the name. To change later, say "switch to \<workspace>".

***

## Option B: connector URL with an API key

Use this when you want the connector fixed to a single workspace.

**Step 1:** [Create an API key](/dapta-mcp/setup/mint-your-api-key.md) and copy the connector URL the admin panel shows. It has this form:

```
https://mcp.dapta.ai/<your-key>/mcp
```

***

**Step 2:** In claude.ai or Claude Desktop go to **Settings**, then **Connectors**, then **Add custom connector**. Name it **Dapta**, paste the URL, leave the OAuth client fields empty and click **Add**.

{% hint style="danger" %}
The connector URL contains your key. Treat it like a password and never share it.
{% endhint %}

With a key, the workspace is fixed by the key and Claude never asks which one to use.

***

## Next step

{% 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-claude-desktop.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.