> 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/gemini_enterprise.md).
# Gemini Enterprise
Bring business data into Gemini Enterprise as a custom MCP data store. Ask questions and generate insights across any Coupler.io source—no SQL required.
Gemini Enterprise is Google Cloud's enterprise AI platform for building agents and analyzing business data through natural language. By connecting Coupler.io to Gemini Enterprise as a custom MCP server, you can pull in data from any source and ask questions, spot trends, and generate insights — no SQL or code required.
## Why use Gemini Enterprise as a destination?
* **Enterprise-grade analysis** — query your business data conversationally inside Google Cloud's governed Gemini Enterprise environment
* **Any source, one data store** — connect Google Ads, TikTok Ads, Google Drive, or any other Coupler.io source, and analyze it all in one place
* **Secure OAuth connection** — Coupler.io issues a dedicated OAuth app so Gemini Enterprise authenticates against the MCP server without sharing database passwords
* **Always fresh data** — schedule your data flow to refresh automatically so Gemini Enterprise always has up-to-date data to work with
## Prerequisites
* A Google Cloud account with access to Gemini Enterprise
* Account **admin or owner** access in Coupler.io to create the OAuth credentials
## Quick start
{% hint style="success" %}
Create the OAuth credentials in Coupler.io first, then set up the custom MCP data store in Google Cloud. Having the credentials ready means you can complete the GCP form in one pass.
{% endhint %}
### How to connect
{% stepper %}
{% step %}
**Add a source to your data flow.** In Coupler.io, create a new data flow and add at least one source — for example, Google Ads, TikTok Ads, or any other supported integration.
{% endstep %}
{% step %}
**Select Gemini Enterprise as the destination.** In the destination step of your data flow, choose **Gemini Enterprise** from the list of available destinations.
{% endstep %}
{% step %}
**Create OAuth credentials in Coupler.io.** Coupler.io issues an OAuth app that Gemini Enterprise uses to authenticate against the MCP server. Copy the **Client ID** and **Client Secret** — the secret is shown only once, so save it now.
{% hint style="info" %}
Only an account admin or owner can create these credentials. If you lose the secret, regenerate it to issue a new one.
{% endhint %}
{% endstep %}
{% step %}
**Open the custom MCP data store flow in Google Cloud.** In Gemini Enterprise, go to **Data stores → Create data store** and choose **Custom MCP server**. See Google's [Set up a custom MCP server](https://docs.cloud.google.com/gemini/enterprise/docs/connectors/custom-mcp-server/set-up-custom-mcp-server) guide for the full walkthrough.
{% endstep %}
{% step %}
**Paste the connection values into the GCP form.** Coupler.io provides the **MCP Server URL**, **Authorization URL**, **Token URL**, and **Scopes** (`mcp`) in the destination step. Add them along with the **Client ID** and **Client Secret** from the previous step.
{% endstep %}
{% step %}
**Run the data flow.** Click **Run** to execute the data flow manually. Once it completes successfully, your data is available to Gemini Enterprise. Open Gemini Enterprise and start asking questions about your dataset.
{% endstep %}
{% endstepper %}
## Supported features
| Feature | Supported |
| -------------------- | --------- |
| Replace mode | Yes |
| Append mode | No |
| Automatic scheduling | Yes |
| Type enforcement | No |
| Templates | No |
## Gemini Enterprise common issues
### Connection issues
Gemini Enterprise can't authenticate against the MCP server
Authentication failures usually mean the OAuth values in the GCP data store form don't match what Coupler.io issued. Check the following:
* Confirm the **Client ID** and **Client Secret** in the GCP form match the OAuth app in the Coupler.io destination step.
* Verify the **Authorization URL**, **Token URL**, and **MCP Server URL** were copied exactly, with no trailing spaces.
* Make sure the **Scopes** field is set to `mcp`.
If you regenerated the client secret in Coupler.io, you must paste the new secret into the GCP data store form — the old one no longer works.
I lost the client secret
The client secret is shown only once, at creation. If you didn't copy it, open the Gemini Enterprise destination step in Coupler.io and click **Regenerate secret** to issue a new one, then paste it into the GCP data store form.
{% hint style="warning" %}
Regenerating the secret keeps existing access tokens valid, but any place already using the old secret to request new tokens will need the new value.
{% endhint %}
I can't create or manage the OAuth credentials
Only an account **admin or owner** can create, regenerate, or delete the OAuth app used for Gemini Enterprise. If the buttons are disabled, ask an admin or owner on your Coupler.io account to set up the credentials.
### Data issues
Gemini Enterprise sees fewer rows than the Coupler.io preview shows
A mismatch between the Preview in Coupler.io and the data Gemini Enterprise receives can occur when the same identifier appears multiple times and deduplication affects the export differently than the preview.
{% hint style="danger" %}
Don't rely on the Preview tab alone to confirm what Gemini Enterprise will receive. Always verify the actual row count after running the flow. You can also configure a Google Sheets export to cross-check the number of rows and see what's missing.
{% endhint %}
If specific rows are missing, note the relevant IDs and contact Coupler.io support with the data flow details — this type of discrepancy requires engineering investigation.
### Permission errors
"You've reached your destination limit" or AI usage is restricted
Coupler.io plans have limits on **destination type**. If you're using Gemini Enterprise as a destination and also sending data elsewhere (for example, Google Sheets), you may hit this limit.
To resolve this, either:
* Remove the other destination and use only Gemini Enterprise, or
* Upgrade to a higher Coupler.io plan that supports multiple destination types.
{% hint style="info" %}
Each active data flow counts toward your plan limits. If you created a test flow with a different destination, delete it to free up your destination slot or upgrade to a higher plan.
{% endhint %}
## Gemini Enterprise FAQ
What is Gemini Enterprise?
Gemini Enterprise is Google Cloud's enterprise AI platform for building agents and analyzing business data in a governed environment. When connected to Coupler.io through a custom MCP server, Gemini Enterprise can access your business data from any supported source.
How does my data get to Gemini Enterprise?
Coupler.io exposes your data through an MCP (Model Context Protocol) server. You register that server in Google Cloud as a custom MCP data store, and Gemini Enterprise authenticates to it using an OAuth app that Coupler.io issues. When you run a data flow with Gemini Enterprise as the destination, the data becomes available through this connection and Gemini Enterprise fetches it on demand.
What do I need to paste into the Google Cloud data store form?
Coupler.io provides everything in the destination step: the **MCP Server URL**, **Authorization URL**, **Token URL**, **Scopes** (`mcp`), plus the **Client ID** and **Client Secret** from the OAuth app you create. Copy these into the custom MCP server form in Gemini Enterprise.
Who can set up the OAuth credentials?
Only an account **admin or owner** in Coupler.io can create, regenerate, or delete the OAuth app used for Gemini Enterprise. Other members can still build and run data flows once the credentials exist.
Can I send data from multiple sources to Gemini Enterprise in one flow?
Yes. A single Coupler.io data flow supports multiple sources, and you can combine them using **Join** or **Append** transformations before the data reaches Gemini Enterprise. This is useful when you want to correlate data from different platforms in one place.
How do I keep Gemini Enterprise's data up to date without re-running manually?
Once your data flow has completed a successful manual run, set up a **schedule** in Coupler.io to refresh the data automatically — hourly, daily, or at a custom interval. Gemini Enterprise will then have access to fresh data whenever it queries the data store.
{% hint style="info" %}
For help setting up specific data sources for Gemini Enterprise, see the individual source articles in the **Sources** section of this Help Center.
{% endhint %}
---
# 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/gemini_enterprise.md?ask=&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.