Skip to main content
hc
Submit
mcpSource-backedReview first Safety ✓ Privacy ✓

gcloud MCP Server

Google Cloud gcloud MCP server from googleapis that lets Claude run approved gcloud CLI commands with allowlist and denylist controls for cloud resource inspection, automation, and operations.

by Google APIs·added 2026-06-06·
Claude CodeClaude Desktop
HarnessClaude CodeClaude Desktop
Review first — review before installing

Open the source and read safety notes before installing.

Safety notes

  • gcloud MCP Server executes gcloud CLI commands with the permissions of the active gcloud account.
  • Allowed commands can create, update, delete, deploy, scale, list, export, or configure Google Cloud resources depending on IAM permissions and selected services.
  • The server blocks command substitution, pipes, redirection, SSH-style commands, interactive commands, and a default set of sensitive command prefixes, but allowed gcloud commands can still have real infrastructure, billing, IAM, and data impact.
  • Use allowlists for narrow workflows and service account impersonation with limited roles when possible.
  • Require human approval for IAM, billing, networking, firewall, storage, database, secret, deployment, delete, and production-impacting commands.

Privacy notes

  • gcloud output can reveal project IDs, resource names, regions, IAM bindings, service accounts, logs, errors, labels, metadata, URLs, secrets references, billing context, and infrastructure topology.
  • Authentication state, ADC files, service account impersonation details, access tokens, project IDs, and local gcloud configuration should stay out of prompts and repository files.
  • Command output may be retained by the MCP client, model provider, terminal logs, shell history, and chat transcripts.
  • Avoid broad listing or export commands against production projects unless data handling and retention have been reviewed.

Prerequisites

  • Node.js 20 or newer with npm or another compatible package runner.
  • Google Cloud CLI installed and authenticated.
  • Active gcloud account, project, and configuration scoped to the intended environment.
  • Least-privilege user or service account impersonation for the allowed cloud actions.
  • Reviewed allowlist or denylist configuration before letting an agent run cloud operations.

Schema details

Install type
cli
Troubleshooting
No
Source repository stats
Scope
Source repo
Collection metadata
Estimated setup
20 minutes
Difficulty
advanced
Tool listing metadata
Disclosure
Preview Google Cloud MCP server hosted in the googleapis organization. The upstream README says the repository provides a solution, is not an officially supported Google product, is not covered under Google Cloud Terms of Service, and may change as MCP and related SDKs evolve.
Full copyable content
{
  "mcpServers": {
    "gcloud": {
      "command": "npx",
      "args": ["-y", "@google-cloud/gcloud-mcp"]
    }
  }
}

About this resource

Content

gcloud MCP Server is a preview Google Cloud MCP server from the googleapis organization. It lets Claude-compatible MCP clients execute approved gcloud CLI commands through a single run_gcloud_command tool, with support for command allowlists and denylists.

Use it when an agent needs Google Cloud context or can help automate a narrow, reviewed cloud workflow. Because gcloud commands can affect real infrastructure, IAM, data, deployments, and billing, configure it with least-privilege credentials and explicit command controls.

Source Review

These sources were reviewed on 2026-06-06. Prefer the live repository, package README, npm registry metadata, license, package manifest, server implementation, run_gcloud_command tool, access-control implementation, gcloud executor, and security policy for current installation and behavior details.

Features

  • Run a single gcloud command at a time through the MCP tool.
  • Use the active gcloud account and configuration on the machine running the server.
  • Install with npx -y @google-cloud/gcloud-mcp.
  • Initialize as a Gemini CLI extension with the package's init command.
  • Configure allowlists and denylists for command prefixes.
  • Use default denials for commands that are interactive, sensitive, or inappropriate for autonomous agents.
  • Reject shell command substitution, pipes, and redirection.
  • Ask for access-control details through the debug config command.

Installation

Install Node.js 20 or newer and the Google Cloud CLI, then authenticate gcloud with a user or service-account impersonation path scoped to the intended work.

Add the server to an MCP client:

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

Claude Code users can add it with:

claude mcp add gcloud -- npx -y @google-cloud/gcloud-mcp

Review allowlist and denylist configuration before using the server against shared or production Google Cloud projects.

Use Cases

  • Ask Claude to list narrowly scoped Google Cloud resources.
  • Inspect configuration for a project, service, deployment, or region.
  • Generate and run a reviewed gcloud command for a routine operational task.
  • Query resource metadata with JSON output projections.
  • Debug permissions or project configuration with a human approving each step.
  • Automate a narrow runbook with an allowlist and service-account impersonation.

Safety and Privacy

gcloud MCP Server is active cloud automation. Even with its default denylist, commands that remain permitted can change infrastructure, expose data, affect availability, alter IAM, trigger spend, deploy code, or delete resources if the active account has those permissions.

Use service-account impersonation and least-privilege roles rather than a broad personal account. Prefer allowlists for routine workflows, keep production projects separate from experiments, and require human approval for commands that can mutate resources or reveal sensitive data.

Do not paste credentials, access tokens, private project details, or secret values into prompts. Treat gcloud command output as sensitive because it can include infrastructure topology, IAM bindings, resource names, logs, and other operational context.

Duplicate Check

Existing entries cover BigQuery, Firebase, Google Analytics, Google Workspace, MCP Toolbox for Databases, and other cloud or database servers, but no gcloud MCP Server entry, googleapis/gcloud-mcp, @google-cloud/gcloud-mcp, or matching source URL was found in content/mcp.

#google-cloud#gcloud#cloud#devops#infrastructure

Source citations

Signals

Loading live community signals…

More like this, weekly

A short, calm digest of reviewed Claude resources. Unsubscribe any time.