Gemini Cloud Assist

What can you do with Gemini Cloud Assist MCP?

- Ask general Google Cloud questions— Get guidance on best practices, architectures, and operations usingask_cloud_assist.
- Design and architect infrastructure— Describe your requirements and usedesign_infrato create infrastructure configurations for Google Cloud.
- Troubleshoot cloud issues— Run deep investigations to find root causes of problems in your environment withinvestigate_issue.
- Manage cloud resources— Create, update, or delete Google Cloud resources directly throughinvoke_operationwhen Agent Actions are enabled.
- Analyze and optimize costs— Get spend breakdowns and identify cost-saving opportunities like idle resources usingoptimize_costs.
- Deploy verified infrastructure designs— Usemanage_applicationto deploy a design after validating it withassess_best_practices.

[!IMPORTANT]Private Preview NoticeThe Gemini Cloud Assist MCP server APIs are currently in Private Preview and are behind an allowlist. Please contact your Google Cloud account team to request access.

[!WARNING]Deprecation Notice & Migration to Remote MCP Server

The Gemini Cloud Assist MCP server has migrated from a local Node.js architecture to a Remote MCP Server architecture. The older local Node.js server will lose support in the coming months.

To use the new Remote MCP Servers, please use versionv0.8.0or later. If you wish to continue using the legacy local server during the transition, please pin your configuration to older versions.

This server connectsModel Context Protocol (MCP)clients such as theGemini CLIto theGemini Cloud Assist APIs. It allows you to use natural language to understand, manage, and troubleshoot your Google Cloud environment directly from the local command line.

[!NOTE] TheGoogle Cloud Platform Terms of Service(available athttps://cloud.google.com/terms/) and theData Processing and Security Terms(available athttps://cloud.google.com/terms/data-processing-terms) do not apply to any component of the Gemini Cloud Assist MCP Server software.

To learn more about Gemini Cloud Assist, see theGemini Cloud Assist overviewin the Google Cloud documentation.

- Google Cloud SDKinstalled and configured.
- AGoogle Cloud project.
- The followingIAM roleson your user account:

# Authenticate your user account to the gcloud CLI gcloud auth login # Set up Application Default Credentials for the server. gcloud auth application-default login

Install the MCP server as aGemini CLI extension:

gemini extensions install https://github.com/GoogleCloudPlatform/gemini-cloud-assist-mcp

"mcpServers": { "gemini_cloud_assist": { "httpUrl": "https://geminicloudassist.googleapis.com/mcp", "authProviderType": "google_credentials", "oauth": { "scopes": ["https://www.googleapis.com/auth/cloud-platform"] }, "timeout": 600000 }, "application_design_center": { "httpUrl": "https://designcenter.googleapis.com/mcp", "authProviderType": "google_credentials", "oauth": { "scopes": ["https://www.googleapis.com/auth/cloud-platform"] }, "timeout": 600000 } }

Add the following to yourmcp_config.json:

"mcpServers": { "gemini_cloud_assist": { "serverUrl": "https://geminicloudassist.googleapis.com/mcp", "headers": {}, "authProviderType": "google_credentials" }, "application_design_center": { "serverUrl": "https://designcenter.googleapis.com/mcp", "headers": {}, "authProviderType": "google_credentials" } }

- In your Google Cloud project, create an OAuth 2.0 client ID for a desktop app.
- ConfigureURI://anysphere.cursor-mcp/oauth/callbackas the redirect URL.
- Add or merge the following configuration block:

{ "mcpServers": { "gemini_cloud_assist": { "url": "https://geminicloudassist.googleapis.com/mcp", "auth": { "CLIENT_ID": "${env:OAUTH_CLIENT_ID}", "CLIENT_SECRET": "${env:OAUTH_CLIENT_SECRET}", "scopes": ["https://www.googleapis.com/auth/cloud-platform"] } }, "application_design_center": { "url": "https://designcenter.googleapis.com/mcp", "auth": { "CLIENT_ID": "${env:OAUTH_CLIENT_ID}", "CLIENT_SECRET": "${env:OAUTH_CLIENT_SECRET}", "scopes": ["https://www.googleapis.com/auth/cloud-platform"] } } } }

Follow the configuration instructions for your specific application:

Gemini Cloud Assist is an agent accessible through a set of MCP tools. The agent invoked by MCP tool calls makes its own tool calls internally to Google Cloud. The followingMCP toolsare published for agents to consume:

Application Design Center MCPtools, often orchestrated by GCA’s design_infra tool, manages the infrastructure application lifecycle using Application Design Center, including template management, security compliance and remediation and deployment.

- If you encounter a bug, please file an issue on ourGitHub Issuespage.
- Before sending a pull request, please review ourContributing Guide.

This project is licensed under the Apache 2.0 License and provided as-is, without warranty or representation for any use or purpose. For details, see theLICENSEfile.

Verified GPU compute for humans, applications, and agents.