> For the complete documentation index, see [llms.txt](https://docs.coupler.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.coupler.io/destinations/categories/ai/cursor.md).

# Cursor

Connect Coupler.io to Cursor AI editor using Model Context Protocol. Query your data flows with natural language—no SQL needed.

Cursor is an AI-powered code editor that lets you interact with data through natural language. By connecting Coupler.io to Cursor, you can load data from any source directly into your AI workspace and ask questions about it — no SQL, no formulas, just conversation.

The integration uses the **Model Context Protocol (MCP)**, which lets Cursor communicate with Coupler.io as a remote data provider. Your data flows become queryable datasets that Cursor's AI can reason over.

## Why use Cursor as a destination?

* **Conversational analytics** — Ask questions like "what's my top-performing campaign this month?" instead of writing queries
* **Any source, one workspace** — Marketing reports, financial metrics, operational data, or any other Coupler.io source all land in the same AI-ready environment
* **No code required** — Analysts and non-technical users can explore complex datasets without leaving Cursor
* **Live data, real insights** — Schedule your data flow to refresh automatically, so Cursor always has up-to-date data to work with

## Prerequisites

* A Cursor account
* The Cursor desktop application installed on your machine

## Quick start

{% hint style="success" %}
Install the Coupler.io MCP connector in Cursor before building your data flow — authentication happens on the Cursor side first, then you select Cursor as the destination in Coupler.io.
{% endhint %}

## How to connect

{% stepper %}
{% step %}
**Install the Coupler.io MCP connector in Cursor and authenticate.** Visit the [Coupler.io entry in the Cursor MCP directory](https://l.rw.rw/couplerio-cursor-mcp) and click **Add to Cursor**. Once added, find the new integration inside Cursor and click **Needs authentication**. Sign in with your Coupler.io credentials and grant access.
{% endstep %}

{% step %}
**Create a data flow in Coupler.io.** In Coupler.io, create a new data flow and add your data source, such as Google Analytics, HubSpot, Airtable, or others.
{% endstep %}

{% step %}
**Select Cursor as the destination.** In the destination step of your data flow, choose **Cursor** from the list of available destinations.
{% endstep %}

{% step %}
**Run the data flow.** Click **Run** to execute the data flow manually. Once it completes successfully, your data is available in Cursor's AI context.
{% endstep %}

{% step %}
**Explore your data in Cursor.** Open the AI Pane in Cursor from the side panel or command palette. Start asking questions about your dataset — for example, "summarize my sales data by region" or "which rows have missing values?"
{% endstep %}
{% endstepper %}

## Supported features

| Feature              | Supported |
| -------------------- | --------- |
| Replace mode         | Yes       |
| Append mode          | No        |
| Automatic scheduling | Yes       |
| Type enforcement     | No        |
| Templates            | No        |

## Cursor common issues

### Connection issues

<details>

<summary>"Needs authentication" never resolves after signing in</summary>

This usually means the OAuth handshake between Cursor and Coupler.io didn't complete. Try removing the Coupler.io MCP entry from Cursor, reloading the app, and re-adding Coupler.io MCP from the MCP directory. Make sure you're signing in with the correct Coupler.io account and that pop-ups or redirects are not being blocked by your browser.

</details>

<details>

<summary>MCP connector shows as installed but Cursor has no access to data</summary>

The MCP connector being installed does not automatically load data — you still need to create and successfully run a data flow in Coupler.io with Cursor selected as the destination. Check that your data flow has completed at least one successful run before querying in Cursor.

</details>

### Data issues

<details>

<summary>Cursor's AI gives incomplete or inaccurate answers about my data</summary>

The quality of answers depends on the structure of the data coming from Coupler.io. Make sure column names are descriptive (e.g., `revenue_usd` rather than `col_3`) and that your data flow applies any necessary transformations — like aggregations or joins — before it reaches Cursor. Cleaner, well-labeled data produces better conversational results.

Also, make sure you are using the right prompt. Vague and abstract prompts result in poor answers.

</details>

<details>

<summary>Data in Cursor appears outdated</summary>

Cursor shows the data from the most recent successful run of your data flow. If the data looks stale, go back to Coupler.io and trigger a manual run to refresh it. Once you've confirmed the data flow works correctly, you can set up a schedule so Cursor always has current data.

Make sure to start a new chat to fetch fresh data or ask Cursor to get it directly if you want to continue the ongoing conversation.

</details>

### Permission errors

<details>

<summary>"Access denied" when Cursor tries to call the Coupler.io MCP</summary>

This error typically appears when the authentication token has expired or been revoked. Re-authenticate by clicking **Needs authentication** on the Coupler.io MCP entry in Cursor. If the issue persists, remove and re-add the integration from the Cursor MCP directory.

{% hint style="danger" %}
Do not share your Coupler.io credentials with Cursor's AI chat directly — authentication should only happen through the official MCP connector flow.
{% endhint %}

</details>

## Cursor FAQ

<details>

<summary>What is MCP and why does the Cursor integration use it?</summary>

MCP stands for Model Context Protocol — an open standard that lets AI applications like Cursor communicate with external data providers in a structured way. Instead of copy-pasting data into a chat window, the MCP connector gives Cursor's AI direct, secure access to your Coupler.io data flows. You get richer, more accurate answers because the AI can query the actual dataset rather than working from a snapshot you manually pasted.

</details>

<details>

<summary>Do I need to know how to code to use Coupler.io with Cursor?</summary>

No. The whole point of this integration is to replace code with conversation. Once your data flow is running and the MCP connector is set up, you interact with your data by typing plain-language questions in the Cursor's AI Pane. Cursor is a code editor, but you don't need to write any code to analyze data this way.

</details>

<details>

<summary>Can I send data from multiple sources into Cursor?</summary>

Yes. A single Coupler.io data flow can include multiple sources — for example, combining HubSpot deals with Google Sheets revenue data. You can use Join or Append transformations to shape the combined dataset before it reaches Cursor. This means you can ask Cursor questions that span multiple systems without switching between tools.

</details>

<details>

<summary>What kinds of questions can I ask Cursor about my data?</summary>

You can ask Cursor to summarize, filter, compare, spot trends, or flag anomalies in your dataset. For example: "which marketing channel drove the most signups last quarter?", "are there any rows where revenue is missing?", or "show me the top 10 customers by order value". The more clearly labeled your data is, the more precise the answers will be.

</details>

<details>

<summary>How do I keep my data fresh in Cursor?</summary>

After your first successful manual run, set up a schedule in Coupler.io. Each scheduled run refreshes the data that Cursor can access through the MCP connector. Choose a frequency that matches how often your source data changes — hourly for live dashboards, daily for most reporting use cases.

Every time you start a new chat about your data, Cursor fetches the fresh portion of it. If you want to get updated data in the ongoing conversation, ask Cursor to get it.

</details>

<details>

<summary>Is my data stored inside Cursor?</summary>

No. Cursor accesses your data through the Coupler.io MCP connector at query time — the data itself lives in Coupler.io, not inside the Cursor application. This means your data governance policies and Coupler.io access controls still apply.

</details>


---

# 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.coupler.io/destinations/categories/ai/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.
