> 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/cursor.md).

# Cursor

Connect Cursor to Data Product MCP for AI-assisted discovery and queries.

Connecting Cursor to Data Product MCP lets its agents answer from governed products instead of guessing: discovery, querying, quality, lineage, and owner lookup against trusted, authorized data. From a product page, select **Activate → MCP**, then **View install guide** on the Cursor card.

## What you need

Cursor installed and signed in, your DataOS instance URL, and a [DataOS API token](/consume/get-started/before-you-begin.md). The OAuth method below does not need a token.

## Connect

1. In DataOS, open **Connect to Data Product MCP**, from the **Access developer tools** section of the home page or from the Data Product MCP tools section, then select **Cursor**.
2. Select **Open in Cursor**. Cursor opens its settings with an **Install MCP Server?** prompt, pre-filled with the server name `DataProduct-MCP`, type `streamableHttp`, and your instance URL.
3. Under **Headers**, replace the `<API_TOKEN>` placeholder with your DataOS API token.
4. Select **Install**.

Cursor lists **DataProduct-MCP** under **Installed MCP Servers** with its tools enabled. If the toggle is off, turn it on.

{% hint style="warning" %}
[API tokens](https://v2.dataos.info/references/key-concepts/api-tokens) are secrets. Cursor stores server config in user-level settings, which keeps the token out of project files. If you copy the configuration into a project file instead, add it to `.gitignore`.
{% endhint %}

## Alternative: add the server manually

Configure the server directly in Cursor instead of using the install handoff, with either authentication method. OAuth authorizes in your browser and needs no API token. The API token configuration sets the same values the handoff fills in for you.

1. In Cursor, go to **Tools & MCP** and, under **Installed MCP Servers**, select **New MCP Server**.
2. Paste the configuration, replacing the placeholders, and save:

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

```json
{
  "mcpServers": {
    "DataProduct-MCP": {
      "url": "https://<instance-url>/mcp/api/v1"
    }
  }
}
```

Cursor prompts you to authorize in a browser window after you save.
{% endtab %}

{% tab title="API Token" %}

```json
{
  "mcpServers": {
    "DataProduct-MCP": {
      "url": "https://<instance-url>/dataproduct-mcp/api/v1",
      "headers": {
        "apikey": "<API_TOKEN>"
      }
    }
  }
}
```

{% endtab %}
{% endtabs %}

3. Under **Installed MCP Servers**, turn on **DataProduct-MCP**.

## Verify

Open a new chat and ask `What data products are available to consume?`. A working connection returns products and lets Cursor call Data Product MCP tools in follow-up prompts, for example:

* `What data products exist for supplier performance?`
* `Is the orders360 data product fresh and healthy?`
* `What was net revenue by customer segment last quarter?`
* `Who owns this data product if a quality check is failing?`

Next: [Discover in natural language](/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/cursor.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.