gcloud MCP Server ☁️

The gcloud Model Context Protocol (MCP) server enables AI assistants to easily interact with the Google Cloud environment using the gcloud CLI. With the gcloud MCP server you can:

• Interact with Google Cloud using natural language. Describe the outcome you want instead of memorizing complex command syntax, flags, and arguments.
• Automate and simplify complex workflows. Chain multiple cloud operations into a single, repeatable command to reduce manual effort and the chance of error.
• Lower the barrier to entry for cloud management. Empower team members who are less familiar with gcloud to perform powerful actions confidently and safely.

📡 Available MCP Servers

This repository also hosts other MCP servers in addition to the gcloud MCP server. An up to date list is below, and links to other Google Cloud MCP servers hosted outside of this repo are here.

MCP Server Name	Description	Package Name	Version
gcloud	Interact with Google Cloud via the gcloud CLI using natural language prompts.	gcloud-mcp
observability	Access Google Cloud Observability APIs to query logs, metrics, and traces.	observability-mcp

🚀 Getting Started

Prerequisites

• Node.js: version 20 or higher
• gcloud CLI

✨ Set up your MCP server

Gemini CLI and Gemini Code Assist

To integrate MCP servers with Gemini CLI or Gemini Code Assist, run the setup command below from your home directory for MCP server listed in the table. This will install the MCP server as a Gemini CLI extension. for the current user, making it available for all your projects.

npx @google-cloud/[PACKAGE_NAME] init --agent=gemini-cli

For example, for the gcloud-mcp:

npx @google-cloud/gcloud-mcp init --agent=gemini-cli

After the initialization process, you can verify that the gcloud-mcp server is configured correctly by running the following command:

gemini mcp list

> ✓ gcloud: npx -y @google-cloud/gcloud-mcp (stdio) - Connected

For other AI clients

To use MCP servers in this repo with other clients, add the following snippet to their respective JSON configuration files for each MCP server:

"[SERVER_NAME]": {
  "command": "npx",
  "args": ["-y", "@google-cloud/[PACKAGE_NAME]"]
}

For example, for gcloud:

"gcloud": {
  "command": "npx",
  "args": ["-y", "@google-cloud/gcloud-mcp"]
}

Instructions for popular tools:

• Claude Desktop: Open Claude > Settings > Developer > Edit Config and edit claude_desktop_config.json.
• Cline: Click the MCP Servers icon, then Configure MCP Servers to edit cline_mcp_settings.json.
• Cursor: Edit .cursor/mcp.json for a single project or ~/.cursor/mcp.json for all projects.
• Gemini CLI (Manual Setup): If not using extensions, edit .gemini/settings.json for a single project or ~/.gemini/settings.json for all projects.

For Visual Studio Code edit the .vscode/mcp.json file in your workspace for a single project or your global user settings file for all projects:

"servers": {
  "[SERVER_NAME]": {
    "command": "npx",
    "args": ["-y", "@google-cloud/[PACKAGE_NAME]"]
  }
}

For example, for gcloud and observability:

"servers": {
  "gcloud": {
    "command": "npx",
    "args": ["-y", "@google-cloud/gcloud-mcp"]
  },
  "observability": {
    "command": "npx",
    "args": ["-y", "@google-cloud/observability-mcp"]
  },
}

🛠 Local Development

For more information regarding installing the repository locally, please see development.md

🧰 Available MCP Tools

MCP Server	Tool	Description
gcloud	run_gcloud_command	Executes a gcloud command. Some commands have been restricted from execution by the agent. See MCP Permissions for more information.
observability	list_log_entries	Lists log entries from a project.
	list_log_names	Lists log names from a project.
	list_buckets	Lists log buckets from a project.
	list_views	Lists log views from a project.
	list_sinks	Lists log sinks from a project.
	list_log_scopes	Lists log scopes from a project.
	list_metric_descriptors	Lists metric descriptors for a project.
	list_time_series	Lists time series data for a given metric.
	list_alert_policies	Lists the alert policies in a project.
	list_traces	Searches for traces in a project.
	get_trace	Gets a specific trace by id in a project.
	list_group_stats	Lists the error groups for a project.

🔑 MCP Permissions

The permissions of the gcloud MCP are directly tied to the permissions of the active gcloud account. To restrict permissions and operate with the principle of least privilege, you can authorize as a service account using impersonation and assign the service account a role with limited permissions.

By default, the gcloud MCP prevents execution of gcloud commands that don't make sense for AI agents. This is done to restrict commands that can run arbitrary inputs and initiate interactive sessions. See here for the list of denied commands.

💫 Other Google Cloud MCP Servers

Google Cloud offers these other servers:

• Firebase MCP
• Google Analytics MCP
• Google Cloud Genmedia MCP
• Google Cloud Run MCP
• Google Kubernetes Engine (GKE) MCP
• Google Security Operations and Threat Intelligence MCP
• MCP Toolbox for Databases

👥 Contributing

We welcome contributions! Whether you're fixing bugs, sharing feedback, or improving documentation, your contributions are welcome. Please read our Contributing Guide to get started.

📄 Important Notes

This repository is currently in preview and may see breaking changes. This repository provides a solution, not an officially supported Google product. It is not covered under Google Cloud Terms of Service. It may break when the MCP specification, other SDKs, or when other solutions and products change. See also our Security Policy.