Use the Gemini Cloud Assist remote MCP server

Preview

This feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms, and the Additional Terms for Generative AI Preview Products. Pre-GA features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Important: Integrating Gemini Cloud Assist with third-party tools using MCP is in private preview. To request access, contact your Google Cloud account team.

Use of this Preview offering of Gemini Cloud Assist is subject to the Google Cloud Agreement, including the Pre-GA Offering Terms of the Google Cloud Specific Service Terms, as supplemented by the terms for the Gemini for Google Cloud Trusted Tester Program.

This document shows you how to use the Gemini Cloud Assist remote Model Context Protocol (MCP) server to connect with AI applications including Gemini CLI, ChatGPT, Claude, and custom applications you are developing. The Gemini Cloud Assist remote MCP server helps you design infrastructure, investigate issues, manage resources, and optimize costs.

We recommend that you use the App Design Center MCP server and the Gemini Cloud Assist MCP server together to design and deploy applications.

Model Context Protocol (MCP) standardizes how large language models (LLMs) and AI applications or agents connect to external data sources. MCP servers let you use their tools, resources, and prompts to take actions and get updated data from their backend service.

What's the difference between local and remote MCP servers?

Local MCP servers

Typically run on your local machine and use the standard input and output streams (stdio) for communication between services on the same device.

Remote MCP servers

Run on the service's infrastructure and offer an HTTP endpoint to AI applications for communication between the AI MCP client and the MCP server. For more information about MCP architecture, see MCP architecture.

Google and Google Cloud remote MCP servers

Google and Google Cloud remote MCP servers have the following features and benefits:

• Simplified, centralized discovery
• Managed global or regional HTTP endpoints
• Fine-grained authorization
• Optional prompt and response security with Model Armor protection
• Centralized audit logging

For information about other MCP servers and information about security and governance controls available for Google Cloud MCP servers, see Google Cloud MCP servers overview.

Before you begin

Sign in to your Google Cloud account. If you're new to Google Cloud, create an account to evaluate how our products perform in real-world scenarios. New customers also get $300 in free credits to run, test, and deploy workloads.

Install the Google Cloud CLI. After installation, initialize the Google Cloud CLI by running the following command:

gcloud init

If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

Install the Google Cloud CLI. After installation, initialize the Google Cloud CLI by running the following command:

gcloud init

If you're using an external identity provider (IdP), you must first sign in to the gcloud CLI with your federated identity.

Enable the API

Enable the Gemini Cloud Assist service in your project:

gcloud services enable geminicloudassist.googleapis.com \
    --project=PROJECT_ID

Replace PROJECT_ID with your Google Cloud project ID.

Required roles

To get the permissions that you need to use the Gemini Cloud Assist MCP server, ask your administrator to grant you the following IAM roles on the project where you want to use the Gemini Cloud Assist MCP server:

• Make MCP tool calls: MCP Tool User (roles/mcp.toolUser)
• Use Gemini Cloud Assist: one of Gemini Cloud Assist User (roles/geminicloudassist.user), Gemini Cloud Assist Editor (roles/geminicloudassist.editor), or Gemini Cloud Assist Admin (roles/geminicloudassist.admin)

For more information about granting roles, see Manage access to projects, folders, and organizations.

These predefined roles contain the permissions required to use the Gemini Cloud Assist MCP server. To see the exact permissions that are required, expand the Required permissions section:

Required permissions

The following permissions are required to use the Gemini Cloud Assist MCP server:

• Make MCP tool calls: mcp.tools.call

You might also be able to get these permissions with custom roles or other predefined roles.

Authentication and authorization

The Gemini Cloud Assist remote MCP server uses the OAuth 2.0 protocol with Identity and Access Management (IAM) for authentication and authorization. All Google Cloud identities are supported for authentication to MCP servers.

Gemini Cloud Assist doesn't support API keys as an authentication method.

We recommend that you create a separate identity for agents that are using MCP tools so that access to resources can be controlled and monitored. For more information about authentication, see Authenticate to MCP servers.

Gemini Cloud Assist MCP OAuth scopes

OAuth 2.0 uses scopes and credentials to determine if an authenticated principal is authorized to take a specific action on a resource. For more information about OAuth 2.0 scopes at Google, read Using OAuth 2.0 to access Google APIs.

Gemini Cloud Assist has the following MCP tool OAuth scope:

Scope URI for gcloud CLI	Description
https://www.googleapis.com/auth/cloud-platform	Read and write data.

Configure an MCP client to use the Gemini Cloud Assist MCP server

AI applications and agents, such as Claude or Gemini CLI, can instantiate an MCP client that connects to a single MCP server. An AI application can have multiple clients that connect to different MCP servers. To connect to a remote MCP server, the MCP client must know the remote MCP server's URL.

In your AI application, connect to a remote MCP server. You are prompted to enter details about the server, such as its name and URL.

For the Gemini Cloud Assist MCP server, enter the following as required:

Configuration property	Value
Server name	gemini-cloud-assist
Server URL or endpoint	https://geminicloudassist.googleapis.com/mcp
Transport	HTTP
Authentication details	Depending on how you want to authenticate, you can enter your Google Cloud credentials, your OAuth Client ID and secret, or an agent identity and credentials. For more information, see Authenticate to MCP servers.
OAuth scope	The OAuth 2.0 scope used when connecting to the Gemini Cloud Assist MCP server.

For host-specific guidance about setting up and connecting to MCP server, see the following:

• Claude.ai
• Gemini CLI

For more general guidance, see the following resources:

• Connect to remote MCP servers.
• Configure MCP in an AI application.

Available tools

To view details of available MCP tools and their descriptions for the Gemini Cloud Assist MCP server, see the Gemini Cloud Assist MCP reference.

List tools

Use the MCP inspector to list tools, or send a tools/list HTTP request directly to the Gemini Cloud Assist remote MCP server. The tools/list method doesn't require authentication.

POST /mcp HTTP/1.1
Host: geminicloudassist.googleapis.com
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "method": "tools/list",
}

Example use cases

The following are example use cases for the Gemini Cloud Assist MCP server:

• Access product knowledge and best practices: get advice for using and configuring Google Cloud products.

  User prompt: What storage class should I use for my data?

  Agent action: the agent identifies and presents best practices.

• Inspect your resources, applications, and data: ask about configurations and metrics for your resources.

  User prompt: List all config changes in the last 24 hours.

  Agent action: the agent inspects your organizations and returns the information you requested.

• Generate infrastructure design based on goals: describe the Google Cloud services you need and the goal you want to achieve.

  User prompt: Help me set up a web application using Cloud Run, Cloud SQL, and Cloud Load Balancing in the eu-west-2 region.

  Agent action: the agent generates an architecture design that fits your goal using the Google Cloud services you want.

Optional security and safety configurations

MCP introduces new security risks and considerations due to the wide variety of actions that you can do with the MCP tools. To minimize and manage these risks, Google Cloud offers default settings and customizable policies to control the use of MCP tools in your Google Cloud organization or project.

For more information about MCP security and governance, see AI security and safety.

Use Model Armor

Model Armor is a Google Cloud service designed to enhance the security and safety of your AI applications. It works by proactively screening LLM prompts and responses, protecting against various risks and supporting responsible AI practices. Whether you are deploying AI in your cloud environment, or on external cloud providers, Model Armor can help you prevent malicious input, verify content safety, protect sensitive data, maintain compliance, and enforce your AI safety and security policies consistently across your diverse AI landscape.

When Model Armor is enabled with logging enabled, Model Armor logs the entire payload. This might expose sensitive information in your logs.

Caution: Model Armor is available in certain regions. When Model Armor is enabled and you use an MCP server in a jurisdiction that Model Armor doesn't support, the routing behavior of the call might be different for different MCP servers. For more information about the behavior of individual MCP servers, see Model Armor supported products.

Enable Model Armor

You must enable Model Armor APIs before you can use Model Armor.

Console

1. Enable the Model Armor API.

   Roles required to enable APIs

   To enable APIs, you need the Service Usage Admin IAM role (roles/serviceusage.serviceUsageAdmin), which contains the serviceusage.services.enable permission. Learn how to grant roles.

   Enable the API

2. Select the project where you want to activate Model Armor.

gcloud

Before you begin, follow these steps using the Google Cloud CLI with the Model Armor API:

1. In the Google Cloud console, activate Cloud Shell.

   Activate Cloud Shell

   At the bottom of the Google Cloud console, a Cloud Shell session starts and displays a command-line prompt. Cloud Shell is a shell environment with the Google Cloud CLI already installed and with values already set for your current project. It can take a few seconds for the session to initialize.

2. Run the following command to set the API endpoint for the Model Armor service.

   gcloud config set api_endpoint_overrides/modelarmor "https://modelarmor.LOCATION.rep.googleapis.com/"

   Replace LOCATION with the region where you want to use Model Armor.

Configure protection for Google and Google Cloud remote MCP servers

To help protect your MCP tool calls and responses you can use Model Armor floor settings. A floor setting defines the minimum security filters that apply across the project. This configuration applies a consistent set of filters to all MCP tool calls and responses within the project.

Tip: Don't enable the prompt injection and jailbreak filter unless your MCP traffic carries natural language data.

Set up a Model Armor floor setting with MCP sanitization enabled. For more information, see Configure Model Armor floor settings.

Note: If the agent and the MCP server are in different projects, you can create floor settings in both projects (the client project and the resource project). In this case, Model Armor is invoked twice, once for each project.

See the following example command:

gcloud model-armor floorsettings update \
--full-uri='projects/PROJECT_ID/locations/global/floorSetting' \
--enable-floor-setting-enforcement=TRUE \
--add-integrated-services=GOOGLE_MCP_SERVER \
--google-mcp-server-enforcement-type=INSPECT_AND_BLOCK \
--enable-google-mcp-server-cloud-logging \
--malicious-uri-filter-settings-enforcement=ENABLED \
--add-rai-settings-filters='[{"confidenceLevel": "MEDIUM_AND_ABOVE", "filterType": "DANGEROUS"}]'

Replace PROJECT_ID with your Google Cloud project ID.

Note the following settings:

• INSPECT_AND_BLOCK: The enforcement type that inspects content for the Google MCP server and blocks prompts and responses that match the filters.
• ENABLED: The setting that enables a filter or enforcement.
• MEDIUM_AND_ABOVE: The confidence level for the Responsible AI - Dangerous filter settings. You can modify this setting, though lower values might result in more false positives. For more information, see Model Armor confidence levels.

Disable scanning MCP traffic with Model Armor

To stop Model Armor from automatically scanning traffic to and from Google MCP servers based on the project's floor settings, run the following command:

gcloud model-armor floorsettings update \
  --full-uri='projects/PROJECT_ID/locations/global/floorSetting' \
  --remove-integrated-services=GOOGLE_MCP_SERVER

Replace PROJECT_ID with the Google Cloud project ID. Model Armor doesn't automatically apply the rules defined in this project's floor settings to any Google MCP server traffic.

Model Armor floor settings and general configuration can impact more than just MCP. Because Model Armor integrates with services like Agent Platform, any changes you make to floor settings can affect traffic scanning and safety behaviors across all integrated services, not just MCP.

Control MCP use with IAM deny policies

Identity and Access Management (IAM) deny policies help you secure Google Cloud remote MCP servers. Configure these policies to block unwanted MCP tool access.

For example, you can deny or allow access based on:

• The principal
• Tool properties like read-only
• The application's OAuth client ID

For more information, see Control MCP use with Identity and Access Management.

What's next

• Read the Gemini Cloud Assist MCP reference documentation.
• Learn more about Google Cloud MCP servers.
• Use the App Design Center MCP server and the Gemini Cloud Assist MCP server together.
• To learn how to use the MCP server in an IDE, see Design and deploy an application using Gemini CLI.