> For the complete documentation index, see [llms.txt](https://v2.dataos.info/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://v2.dataos.info/consume/consume-with-ai/connect-a-client/claude.md).

# Claude

Configure Claude Code or Claude Desktop to connect with Data Product MCP.

Connecting Claude to Data Product MCP lets it answer from governed products instead of guessing: discovery, querying, quality checks, lineage, and owner lookup all run against trusted, authorized data. From a product page, select **Activate → MCP**, then **View install guide** on the Claude Desktop or Claude Code card.

## What you need

Your DataOS instance URL. Claude Code and Claude Desktop need a [DataOS API token](https://v2.dataos.info/consume/get-started/before-you-begin.md) only if you connect with the API token method. Otherwise, they use your DataOS sign-in. On Team and Enterprise plans, your Claude admin must add the connector first.

{% hint style="warning" %}
[API tokens](https://v2.dataos.info/references/key-concepts/api-tokens) are secrets. Do not commit them to source control. Store the token outside your repo or inject it through an environment variable.
{% endhint %}

## Claude Code

Run this in your terminal, replacing the placeholders:

{% hint style="info" %}
Replace `<instance-url>` with your DataOS instance FQDN. For example: `productsandbox.instance.dataos.cloud`.
{% endhint %}

{% tabs %}
{% tab title="OAuth" %}

```bash
claude mcp add --scope user --transport http DataProduct-MCP \
  https://<instance-url>/mcp/api/v1
```

Restart Claude Code, run `/mcp`, select **DataProduct-MCP**, and authorize in the window that opens.
{% endtab %}

{% tab title="API Token" %}
Replace `<API_TOKEN>` with your actual DataOS API token.

```bash
claude mcp add --scope user --transport http DataProduct-MCP \
  https://<instance-url>/dataproduct-mcp/api/v1 --header "apikey: <API_TOKEN>"
```

Restart Claude Code and confirm **DataProduct-MCP** appears in the MCP tools list.
{% endtab %}
{% endtabs %}

`--scope user` installs the server globally for your user account, so it is available across all projects, not just the current folder.

## Claude Desktop

Data Product MCP connects to Claude Desktop and claude.ai as a [custom connector](https://support.claude.com/en/articles/11175166-get-started-with-custom-connectors-using-remote-mcp). Follow the path that matches you:

* **Team or Enterprise member:** your Claude admin adds the connector once for the organization. You [check that it is available and connect](#connect-members) with your own DataOS sign-in.
* **Team or Enterprise admin:** [add the connector](#add-the-connector-admin) so members can connect.
* **Free, Pro, or Max user:** there is no admin, so you [add the connector yourself](#add-the-connector-yourself-free-pro-or-max).
* **Cannot add a custom connector:** [connect with an API token](#alternative-connect-with-an-api-token) through a local configuration file.

### Connect (members)

Your Claude admin may have already added Data Product MCP for your DataOS instance. Check first:

1. In Claude Desktop or on claude.ai, go to **Customize → Connectors**.
2. Search for `DataProduct-MCP`. If it is not listed, see the note below these steps.
3. Select the connector, select **Connect**, and sign in with your DataOS account in the window that opens.
4. In a chat, select **+ → Connectors** and confirm **DataProduct-MCP** is turned on.

{% hint style="warning" %}
**Connector not listed?** Data Product MCP is not enabled for your Claude organization yet. Ask your Claude admin to add it by following [Add the connector (admin)](#add-the-connector-admin), and share your DataOS instance URL with them.
{% endhint %}

{% hint style="info" %}
Because each member signs in with their own DataOS account, Claude returns only the data products that member is authorized to access. The admin who added the connector does not share their access.
{% endhint %}

### Add the connector (admin)

{% hint style="info" %}
On Team plans, only Owners and Primary Owners can add custom connectors. On Enterprise plans, Owners, Primary Owners, and members with a custom role that includes **Manage access to Libraries** can add them.
{% endhint %}

{% stepper %}
{% step %}
In Claude, go to **Organization settings → Connectors**.

<details>

<summary>Show screenshot</summary>

<figure><img src="https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-d4c07f8f917b6dc793a6e21f1381f06c81fe8ae5%2Fclaude-connector-org-settings.png?alt=media" alt="Connectors page in Claude organization settings"><figcaption></figcaption></figure>

</details>
{% endstep %}

{% step %}
Select **Add**, hover over **Custom**, and select **Web**.

<details>

<summary>Show screenshot</summary>

<figure><img src="https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-a02c18645676b8e94e54645863b374a832c1a623%2Fclaude-connector-add-custom-web.png?alt=media" alt="Add menu with Custom expanded to show the Web option"><figcaption></figcaption></figure>

</details>
{% endstep %}

{% step %}
Enter the connector details, then select **Continue**:

* **Name**: `DataProduct-MCP`. Members search for this name in their connectors list. If your organization connects more than one DataOS instance, add the instance to the name, for example `DataProduct-MCP - Product Sandbox`.
* **MCP server URL**: `https://<instance-url>/mcp/api/v1`, replacing `<instance-url>` with your DataOS instance FQDN. For example: `https://productsandbox.instance.dataos.cloud/mcp/api/v1`.

<details>

<summary>Show screenshot</summary>

<figure><img src="https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-a8bd6804672127093dfbfa3ad9862967149ca775%2Fclaude-connector-name-url.png?alt=media" alt="Add custom connector dialog with Name and MCP server URL fields"><figcaption></figcaption></figure>

</details>
{% endstep %}

{% step %}
Keep the detected defaults:

* **Authentication**: **Sign in now**. Each member signs in through DataOS before they can use any tools.
* **OAuth client**: **Use Claude's published identity**.
* **Request headers**: leave empty. Members authenticate through their own DataOS sign-in, so no API token is needed.

<details>

<summary>Show screenshot</summary>

<figure><img src="https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-e08a3df2cb2d7e71850a00a6a9fc34b0fa6e14de%2Fclaude-connector-auth-defaults.png?alt=media" alt="Authentication set to Sign in now and OAuth client set to Use Claude&#x27;s published identity"><figcaption></figcaption></figure>

</details>
{% endstep %}

{% step %}
Select **Add**. **DataProduct-MCP** appears in the connectors list with a **Custom** tag and **Individual** authorization.

<details>

<summary>Show screenshot</summary>

<figure><img src="https://540997223-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FAxLuoblPBpNVcNU4lKPo%2Fuploads%2Fgit-blob-4562654b416c9484b8aa0ac553c48c59d0c5487d%2Fclaude-connector-add.png?alt=media" alt="Add button at the bottom of the Add custom connector dialog"><figcaption></figcaption></figure>

</details>
{% endstep %}
{% endstepper %}

### Add the connector yourself (Free, Pro, or Max)

On a personal plan, there is no admin step. Add the connector yourself:

1. In Claude, go to **Customize → Connectors**.
2. Select **+ Add**, then **Add custom connector**.
3. Enter the name `DataProduct-MCP` and the MCP server URL `https://<instance-url>/mcp/api/v1`, then select **Continue**.
4. Keep the detected defaults (**Sign in now**, **Use Claude's published identity**), leave request headers empty, and select **Add**.
5. Select **Connect** and sign in with your DataOS account.

{% hint style="info" %}
Free plans are limited to one custom connector.
{% endhint %}

### Alternative: connect with an API token

If you cannot add a custom connector, connect Claude Desktop through a local configuration file and a [DataOS API token](https://v2.dataos.info/consume/get-started/before-you-begin.md) instead. This method requires [Node.js](https://nodejs.org/).

1. Install `mcp-remote` globally:

   ```bash
   npm install -g mcp-remote
   ```
2. Open Claude Desktop, go to **Developer** settings, and select **Edit Config**.
3. Paste the configuration below, replace `<instance-url>` with your DataOS instance FQDN and `<API_TOKEN>` with your DataOS API token, then save:

   ```json
   {
     "mcpServers": {
       "DataProduct-MCP": {
         "command": "npx",
         "args": [
           "mcp-remote@latest",
           "https://<instance-url>/dataproduct-mcp/api/v1",
           "--header",
           "apikey: <API_TOKEN>"
         ]
       }
     }
   }
   ```
4. Fully quit and reopen Claude Desktop to apply the configuration.
5. In **Developer** settings, confirm **DataProduct-MCP** appears under configured MCP servers.

## Verify

Ask Claude:

```
What data products are available to consume?
```

Claude returns products from your DataOS instance, scoped to your DataOS access. Next: [Discover in natural language](https://v2.dataos.info/consume/consume-with-ai/discover-in-natural-language.md).


---

# 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://v2.dataos.info/consume/consume-with-ai/connect-a-client/claude.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.
