Google Cloud MCP
Enables interaction with Google Kubernetes Engine (GKE) to list clusters, manage node pools, and retrieve server configurations. It includes automated scripts for deploying and testing sample applications across multiple GKE Autopilot clusters.
What is Google Cloud MCP?
Google Cloud MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables interaction with google kubernetes engine (gke) to list clusters, manage node pools, and retrieve server configurations. it includes automated scripts for deploying and testing sample applicat...
Enables interaction with Google Kubernetes Engine (GKE) to list clusters, manage node pools, and retrieve server configurations. It includes automated scripts for deploying and testing sample applications across multiple GKE Autopilot clusters.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Enables interaction with Google Kubernetes Engine (GKE) to l
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx google-cloud-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Google Cloud MCP
The Google Cloud MCP Server connects AI assistants to eight core Google Cloud Platform services — Billing, Error Reporting, IAM, Logging, Monitoring, Profiler, Spanner, and Trace — through a single MCP interface. It lets you query logs with filters, analyze cost anomalies, test IAM permissions, retrieve distributed traces, and profile application performance all via natural language. Developers and platform engineers use it to reduce context-switching between the GCP console and their AI assistant during incident response, cost reviews, and routine operations.
Prerequisites
- Node.js 18+ and pnpm installed on your machine
- A Google Cloud project with the relevant APIs enabled (Cloud Logging, Monitoring, Billing, IAM, etc.)
- Google Cloud credentials: either run `gcloud auth application-default login` or have a service account key JSON file
- The google-cloud-mcp repository cloned locally (no published npm package)
- An MCP-compatible client such as Claude Desktop
Clone and install dependencies
Clone the repository from GitHub and install all Node.js dependencies using pnpm. The project uses pnpm workspaces, so do not substitute npm or yarn.
git clone https://github.com/krzko/google-cloud-mcp.git
cd google-cloud-mcp
pnpm installAuthenticate with Google Cloud
The server needs valid Google Cloud credentials at runtime. The simplest approach is Application Default Credentials via the gcloud CLI. Alternatively, create a service account, download the JSON key, and set GOOGLE_APPLICATION_CREDENTIALS.
gcloud auth application-default loginBuild the TypeScript project
Compile the TypeScript source to JavaScript. The output is written to the dist/ directory and the entry point used by the MCP config is dist/index.js.
pnpm buildConfigure your MCP client
Add the server to your MCP client configuration file (e.g., claude_desktop_config.json for Claude Desktop). Use the absolute path to the compiled dist/index.js and set the GOOGLE_APPLICATION_CREDENTIALS environment variable if you are using a service account key file.
{
"mcpServers": {
"google-cloud-mcp": {
"command": "node",
"args": ["/absolute/path/to/google-cloud-mcp/dist/index.js"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account-key.json"
}
}
}
}Restart your MCP client and verify connection
Restart Claude Desktop (or your MCP client). The google-cloud-mcp server should appear as connected. You can test it by asking a simple question referencing a real GCP project ID.
Google Cloud MCP Examples
Client configuration
Minimal claude_desktop_config.json entry using Application Default Credentials (no explicit GOOGLE_APPLICATION_CREDENTIALS needed if gcloud auth application-default login was run).
{
"mcpServers": {
"google-cloud-mcp": {
"command": "node",
"args": ["/Users/you/code/google-cloud-mcp/dist/index.js"],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/Users/you/.config/gcloud/application_default_credentials.json"
}
}
}
}Prompts to try
Example natural-language prompts that exercise the server's GCP capabilities.
- "Analyse costs for project my-app-prod-123 for the last 30 days and highlight anomalies"
- "Show me error groups from project my-webapp-prod-789 for the last hour"
- "Test if the service account has storage.buckets.create permission on project data-lake-456"
- "Find logs containing 'database timeout' from project backend-prod-321 from yesterday"
- "Retrieve distributed traces for service checkout-api in project ecom-prod-001 from the last 15 minutes"Troubleshooting Google Cloud MCP
Server starts but returns 'permission denied' or 403 errors when querying GCP
Ensure the authenticated principal (user or service account) has the required IAM roles such as roles/logging.viewer, roles/monitoring.viewer, and roles/billing.viewer. Run `gcloud auth application-default login` again if credentials have expired.
'Cannot find module dist/index.js' error when the MCP client starts the server
You must run `pnpm build` before starting the server. The TypeScript source must be compiled first. Check that the path in your config points to the correct absolute location of the dist/index.js file.
GOOGLE_CLOUD_PROJECT environment variable errors when operations require a project ID
Either pass the project ID explicitly in each prompt (e.g., 'for project my-proj-123') or set the GOOGLE_CLOUD_PROJECT environment variable in your MCP server config's env block.
Frequently Asked Questions about Google Cloud MCP
What is Google Cloud MCP?
Google Cloud MCP is a Model Context Protocol (MCP) server that enables interaction with google kubernetes engine (gke) to list clusters, manage node pools, and retrieve server configurations. it includes automated scripts for deploying and testing sample applications across multiple gke autopilot clusters. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Google Cloud MCP?
Follow the installation instructions on the Google Cloud MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Google Cloud MCP?
Google Cloud MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Google Cloud MCP free to use?
Yes, Google Cloud MCP is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.
Google Cloud MCP Alternatives — Similar Cloud Services Servers
Looking for alternatives to Google Cloud MCP? 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 Google Cloud MCP 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 Google Cloud MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.