Gemini Cloud Assist
An MCP Server for Gemini Cloud Assist; provides tools to assist with your tasks on GCP
What is Gemini Cloud Assist?
Gemini Cloud Assist is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to mcp server for gemini cloud assist; provides tools to assist with your tasks on gcp
An MCP Server for Gemini Cloud Assist; provides tools to assist with your tasks on GCP
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- An MCP Server for Gemini Cloud Assist; provides tools to ass
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gemini-cloud-assistConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Gemini Cloud Assist
The Gemini Cloud Assist MCP server connects any MCP-compatible AI client to Google Cloud's Gemini Cloud Assist APIs, enabling natural-language management, troubleshooting, design, and cost optimization of Google Cloud Platform resources directly from the command line or chat interface. The server exposes five primary tools — ask_cloud_assist, design_infra, investigate_issue, invoke_operation, and optimize_costs — backed by Gemini Cloud Assist's deep integration with GCP services. It is designed for GCP engineers and architects who want to describe infrastructure problems or changes in plain English and have an AI agent handle the GCP API calls, investigations, and Terraform generation.
Prerequisites
- Google Cloud SDK (gcloud CLI) installed and configured
- A Google Cloud project with access requested for the Gemini Cloud Assist Private Preview (contact your Google Cloud account team)
- IAM roles: roles/serviceusage.serviceUsageAdmin and roles/geminicloudassist.user on your user account
- Application Default Credentials configured via gcloud auth application-default login
- An MCP-compatible client such as Gemini CLI, Cursor, or Claude
Authenticate to Google Cloud
Set up both gcloud CLI authentication and Application Default Credentials (ADC). The MCP server uses ADC to authenticate all requests to the Gemini Cloud Assist APIs.
gcloud auth login
gcloud auth application-default loginSet your active project
Ensure your gcloud config points to the GCP project where you have the required IAM roles and where Gemini Cloud Assist access has been granted.
gcloud config set project YOUR_PROJECT_IDConfigure your MCP client for the remote server
The Gemini Cloud Assist MCP server is a Remote MCP Server (as of v0.8.0+). Configure your client to connect to the hosted endpoint using Google OAuth credentials. The server URL is https://geminicloudassist.googleapis.com/mcp.
Add the Application Design Center server (optional)
For infrastructure design and deployment workflows, also add the Application Design Center MCP endpoint. It exposes tools for IaC template management and Security Command Center compliance assessment.
Verify access by asking a GCP question
Start a session in your MCP client and ask a simple GCP question to confirm the server is connected and your credentials are accepted.
Gemini Cloud Assist Examples
Client configuration
Add this configuration to your Gemini CLI settings.json (~/.gemini/settings.json) to connect to both the Gemini Cloud Assist and Application Design Center MCP endpoints.
{
"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
}
}
}Prompts to try
Example prompts that leverage the ask_cloud_assist, investigate_issue, optimize_costs, and design_infra tools:
- "Why are my Cloud Run requests failing with 500 errors in the last hour?"
- "Design a highly available three-tier web application architecture on GCP with Cloud SQL and Cloud Load Balancing"
- "Which of my Compute Engine instances have been idle for more than 7 days?"
- "Show me my top 5 cost drivers this month and suggest optimizations"
- "Create a VPC network with two subnets in us-central1 and europe-west1"Troubleshooting Gemini Cloud Assist
Request denied or 403 error when calling MCP tools
Ensure you have been granted access to the Gemini Cloud Assist Private Preview by your Google Cloud account team. Also verify you have the roles/geminicloudassist.user IAM role on your account in the target project.
ADC credentials not found or expired
Re-run 'gcloud auth application-default login' to refresh your credentials. The server uses ADC, not the gcloud CLI session — both need to be active. Ensure GOOGLE_APPLICATION_CREDENTIALS is not set to a stale service account file.
invoke_operation tool is not available or returns errors
The invoke_operation tool (for creating/updating/deleting GCP resources) requires Agent Actions to be explicitly enabled in your Gemini Cloud Assist configuration. Ask your GCP account team about enabling Agent Actions for your project during the Private Preview.
Frequently Asked Questions about Gemini Cloud Assist
What is Gemini Cloud Assist?
Gemini Cloud Assist is a Model Context Protocol (MCP) server that mcp server for gemini cloud assist; provides tools to assist with your tasks on gcp It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Gemini Cloud Assist?
Follow the installation instructions on the Gemini Cloud Assist GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Gemini Cloud Assist?
Gemini Cloud Assist works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Gemini Cloud Assist free to use?
Yes, Gemini Cloud Assist is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Gemini Cloud Assist Alternatives — Similar Cloud Services Servers
Looking for alternatives to Gemini Cloud Assist? Here are other popular cloud services servers you can use with Claude, Cursor, and VS Code.
Open WebUI
★ 138.2kUser-friendly AI Interface (Supports Ollama, OpenAI API, ...)
Anything LLM
★ 60.4kThe all-in-one AI productivity accelerator. On device and privacy first with no annoying setup or configuration.
LocalAI
★ 46.4kLocalAI is the open-source AI engine. Run any model - LLMs, vision, voice, image, video - on any hardware. No GPU required.
Nacos
★ 33.0kan easy-to-use dynamic service discovery, configuration and service management platform for building AI cloud native applications.
Xiaozhi ESP32
★ 26.7k本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.
Gateway
★ 11.8kA blazing fast AI Gateway with integrated guardrails. Route to 1,600+ LLMs, 50+ AI Guardrails with 1 fast & friendly API.
Browse More Cloud Services MCP Servers
Explore all cloud services servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Gemini Cloud Assist in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Gemini Cloud Assist?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.