> For the complete documentation index, see [llms.txt](https://docs.fusion.vectra.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.fusion.vectra.ai/cloud-onboarding/gcp-cloud-onboarding/quickstart-gcp/context-integration.md).
# Add context integration to Fusion
📘 You need a GCP service account to setup a context integration.: Follow the initial steps below to create one. 1. Create a GCP service account Go to the Service Accounts page Click Create Service Ac
{% hint style="info" %}
**You need a GCP service account to setup a context integration.**
Follow the initial steps below to create one.
{% endhint %}
## 1. Create a GCP service account
1. Go to the Service Accounts page
2. Click **Create Service Account** and follow the steps in the wizard.
3. Create a service account name; your service account ID email address will be auto-created for you.
4. Click **Select a role**, use the **Filter**, type **viewer** into the filter, click **Viewer** to give this service account a **Viewer role**.
Leave the rest set as default.
## 2. Create your service account access keys and export a JSON file
#### The following steps will enable you to automate context configuration in Vectra Fusion.
1. Click **:** to access Actions for your newly created service account, then select **Manage keys**.
2. Click the **Add Key** menu and select **Create new key**
3. Choose **JSON** format. This will enable you to export a file that will automate context configuration in Vectra Fusion and reduce setup to one step.
4. The **JSON** file containing your private key will be auto-downloaded to your computer, delete this file once you're done with it.
## 3. Create a new Context Integration in Vectra Fusion and upload your JSON file.
1. In the Fusion portal, click the ⚙️ -> **Settings** -> **Traffic Sources** -> **Context Integrations** -> **Add Integrations**
2. Select **Google Cloud Provider**
3. Use the "**IMPORT FROM JSON**" button to import your JSON file you exported from GCP.
4. Leave **Zone** blank to automatically include all zones.
5. All fields will be auto-completed and your private key will be imported.
6. Click **Create and Run** to save.
{% hint style="success" %}
**You're done!**
{% endhint %}
Check **Context Labels** to verify your context integration is working as expected
---
# 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.fusion.vectra.ai/cloud-onboarding/gcp-cloud-onboarding/quickstart-gcp/context-integration.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.