> For the complete documentation index, see [llms.txt](https://www.cakewalk.security/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://www.cakewalk.security/docs/ai-agent-access/connections-and-integrations/agent-connections/google-compute-engine.md).

# Google Compute Engine

Connect your company's Google Cloud project to Cakewalk's MCP Gateway. Every agent tool call against Compute Engine passes through the gateway and is evaluated against your Policies.

## Requirements

* Google Cloud project owner or editor who can create OAuth 2.0 clients in **Google Auth Platform**.
* **Compute Engine API** enabled in the project. The MCP server is enabled automatically when the API is on.

## About Scopes

\[VERIFY: confirm with Cakewalk eng before publish; Google does not enumerate the Compute Engine MCP server's scope strings in fetched docs. Standard Google Cloud conventions apply.]

When you create the OAuth client, the Google Auth Platform will associate it with your project's APIs. IAM role on the user account behind the OAuth flow determines what tools the agent can access (e.g., `roles/compute.admin` for full management, `roles/compute.viewer` for read only).

## Step 1: Enable the Compute Engine API

In your Google Cloud project, enable the Compute Engine API. The Compute Engine MCP server activates automatically.

## Step 2: Create the OAuth Client

1. In Google Cloud Console, go to **Google Auth Platform** > **Clients** > **Create client**.
2. For **Application type**, select **Web application**.
3. In the **Authorized redirect URIs** section, click **+ Add URI** and enter:

```
https://mcp-gateway.getcakewalk.io/api/v1/Auth/Callback
```

4. Create the client.

## Step 3: Copy the Client ID and Client Secret

The **OAuth 2.0 client created** dialog shows the credentials. In the **Client secrets** section, copy the secret value. Treat client secrets like passwords and store them in a secure place; Google does not redisplay the secret value.

## Step 4: Paste Credentials Into Cakewalk

1. Open <https://app.getcakewalk.io>.
2. Go to All Connections.
3. Find Google Compute Engine.
4. Click Edit credentials.
5. Paste the Client ID and Client Secret.
6. Save.

## Verifying It Works

The Google Compute Engine Connection card flips to Active on All Connections. From an agent platform connected to Cakewalk, ask the agent to list VM instances in your project. If Compute Engine returns results, the Connection is live.

## Troubleshooting

* Invalid redirect URI on consent: confirm the **Authorized redirect URIs** entry matches `https://mcp-gateway.getcakewalk.io/api/v1/Auth/Callback` exactly.
* Tools return permission denied: the user account behind the OAuth flow must hold the appropriate Compute Engine IAM role on the project.
* Tools return "API not enabled": confirm the Compute Engine API is enabled in the project.

## Learn More

* [Use the Compute Engine remote MCP server](https://docs.cloud.google.com/compute/docs/use-compute-engine-mcp)
* [Authenticate to Google Cloud MCP servers](https://docs.cloud.google.com/mcp/authenticate-mcp)
* [Compute Engine MCP reference](https://docs.cloud.google.com/compute/docs/reference/mcp)


---

# 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://www.cakewalk.security/docs/ai-agent-access/connections-and-integrations/agent-connections/google-compute-engine.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.