> 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/common-issues.md).

# 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Data in Cursor appears outdated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This error typically appears when the authentication token has expired or been revoked.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>


---

# 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://docs.coupler.io/destinations/categories/ai/cursor/common-issues.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.