Google Cloud
A Google Cloud MCP server that enables users to manage Cloud Build and Cloud Run resources. It allows for listing builds and services, as well as retrieving detailed logs and execution status.
What is Google Cloud?
Google Cloud is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to google cloud mcp server that enables users to manage cloud build and cloud run resources. it allows for listing builds and services, as well as retrieving detailed logs and execution status.
A Google Cloud MCP server that enables users to manage Cloud Build and Cloud Run resources. It allows for listing builds and services, as well as retrieving detailed logs and execution status.
This server falls under the Cloud Services category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- A Google Cloud MCP server that enables users to manage Cloud
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx gcloudConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Google Cloud
gcloud-mcp is a Google Cloud MCP server that gives AI assistants direct access to Cloud Build, Cloud Run, Artifact Registry, and Secret Manager resources through 17 purpose-built tools. It authenticates via GCP Application Default Credentials and a GOOGLE_CLOUD_PROJECT environment variable, so no additional API keys need to be stored in the config. Engineers use it to list and inspect builds, fetch per-step logs, view Cloud Run service details and revision history, list Artifact Registry images, and even manually trigger Cloud Build pipelines — all from natural language prompts in Claude. It requires Node.js 20+ and appropriate IAM viewer roles on your GCP project.
Prerequisites
- Node.js 20 or higher installed
- Google Cloud CLI installed and authenticated via 'gcloud auth application-default login'
- A GCP project with the following IAM roles: roles/cloudbuild.builds.viewer, roles/logging.viewer, roles/run.viewer, roles/artifactregistry.reader, roles/secretmanager.viewer
- GOOGLE_CLOUD_PROJECT environment variable set to your GCP project ID
- An MCP-compatible client such as Claude Desktop
Authenticate with Google Cloud Application Default Credentials
Run the gcloud auth command to set up Application Default Credentials on your machine. The MCP server uses these credentials automatically without requiring an explicit API key.
gcloud auth application-default loginVerify required IAM roles are assigned
Ensure your GCP identity (user or service account) has the necessary viewer roles. At minimum you need cloudbuild.builds.viewer and logging.viewer to inspect builds. Add run.viewer for Cloud Run, artifactregistry.reader for Artifact Registry, and secretmanager.viewer for Secret Manager.
gcloud projects get-iam-policy YOUR_PROJECT_ID --flatten="bindings[].members" --format="table(bindings.role,bindings.members)"Add gcloud-mcp to your MCP client configuration
Edit your Claude Desktop config to register the gcloud-mcp server, setting GOOGLE_CLOUD_PROJECT to your target project ID.
Restart Claude Desktop
Quit and relaunch Claude Desktop so it picks up the new MCP server entry and establishes the connection.
Verify access by listing Cloud Run services
In Claude, ask it to list your Cloud Run services or recent builds to confirm the server is authenticated and connected to the correct project.
Google Cloud Examples
Client configuration
Add this block to your claude_desktop_config.json, replacing the project ID with your own:
{
"mcpServers": {
"gcloud-mcp": {
"command": "npx",
"args": ["-y", "@prmichaelsen/gcloud-mcp"],
"env": {
"GOOGLE_CLOUD_PROJECT": "your-gcp-project-id"
}
}
}
}Prompts to try
Once connected, use Claude to manage your GCP resources with natural language:
- "List all Cloud Run services in my project"
- "Show me the last 5 Cloud Build builds and their status"
- "Fetch the build logs for build ID abc123"
- "What Cloud Run revisions are deployed for the 'api' service?"
- "List all Artifact Registry repositories in us-central1"
- "Trigger Cloud Build trigger ID xyz456 on the main branch"Troubleshooting Google Cloud
Authentication errors or 'credentials not found' when querying GCP resources
Run 'gcloud auth application-default login' to refresh your Application Default Credentials. Verify the credentials file exists at ~/.config/gcloud/application_default_credentials.json. The MCP server inherits ADC from the environment, so the credentials must be valid before starting Claude Desktop.
Permission denied errors on specific tools like gcloud_list_builds or gcloud_get_service_logs
Each tool requires specific IAM roles. For build logs you need roles/logging.viewer in addition to roles/cloudbuild.builds.viewer. For Cloud Run details, add roles/run.viewer. Use 'gcloud projects get-iam-policy' to audit your current role assignments.
Frequently Asked Questions about Google Cloud
What is Google Cloud?
Google Cloud is a Model Context Protocol (MCP) server that google cloud mcp server that enables users to manage cloud build and cloud run resources. it allows for listing builds and services, as well as retrieving detailed logs and execution status. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Google Cloud?
Follow the installation instructions on the Google Cloud GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Google Cloud?
Google Cloud works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Google Cloud free to use?
Yes, Google Cloud is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
Google Cloud Alternatives — Similar Cloud Services Servers
Looking for alternatives to Google Cloud? 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 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?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.