> For the complete documentation index, see [llms.txt](https://dataflint.gitbook.io/dataflint-for-spark/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://dataflint.gitbook.io/dataflint-for-spark/dataflint-analyze-your-job/analyze-your-job-in-cursor.md).

# Analyze Your Job in Cursor

### Summary

This guide walks you through using DataFlint Analyze Your Job in Cursor.

You need a DataFlint account. Create one at <https://www.dataflint.io/get-started>. Afterward you will get the following email:

<figure><img src="/files/sR1s9oYNhWFbgurU5sQ2" alt=""><figcaption></figcaption></figure>

### Step-by-step guide

#### 1. Run the prompt from your intro email

Paste the prompt from your intro email into the Cursor agent window.

<figure><img src="/files/xdmyqhDFiasjl5VLm0xp" alt=""><figcaption></figcaption></figure>

#### 2. Review the MCP setup message

The agent confirms that it added the MCP and shows how to enable it.

<figure><img src="/files/A4zTlVhtE3PdKEo8XeU4" alt=""><figcaption></figcaption></figure>

#### 3. Open Settings

Press the settings button.

<figure><img src="/files/SpGxiw6PFwuuAhkxA7sw" alt=""><figcaption></figcaption></figure>

#### 4. Enable the DataFlint MCP

Open **Tools & MCP** and enable `dataflint-selfserve`.

<figure><img src="/files/qAHQYjX1h90SDJFbDTAL" alt=""><figcaption></figcaption></figure>

#### 5. Connect the MCP

Press **Connect**.

<figure><img src="/files/ISdKse5MYvuYoXXt9XH8" alt=""><figcaption></figcaption></figure>

#### 6. Continue in the browser

In the browser tab that opens, select the checkbox and press **Continue**.

<figure><img src="/files/8CNngwRg9lPnHXS0OGMg" alt=""><figcaption></figcaption></figure>

#### 7. Return to Cursor

Press **Open Cursor.app**.

<figure><img src="/files/agjdMfrAKBJQyXSESz2f" alt=""><figcaption></figcaption></figure>

#### 8. Confirm the MCP is running

You should now see the MCP running in Cursor with **3 tools enabled**.

<figure><img src="/files/iMCSVOfBQfNADetftFGs" alt=""><figcaption></figcaption></figure>

#### 9. Continue in the agent window

Return to the agent window and tell the agent to continue.

<figure><img src="/files/kNiBbGCMdW7KobPOxxjx" alt=""><figcaption></figcaption></figure>

Complete the process, until you see that the spark event log upload succeeded

![](/files/g3oq9WF2iSAeW49fJ5nt)&#x20;

Afterward you will get a second email with link for your DataFlint AI job analysis, and a next step of optimizing your job via DataFlint Copilot


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://dataflint.gitbook.io/dataflint-for-spark/dataflint-analyze-your-job/analyze-your-job-in-cursor.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.