Google Cloud MCP

Interact with Google Cloud services and manage your cloud resources.

- Run gcloud CLI commands— Ask your AI to execute any allowedgcloudcommand viarun_gcloud_commandto manage Google Cloud resources.
- Query Cloud Observability data— Retrieve logs, metrics, traces, and alert policies using tools likelist_log_entries,list_time_series, andlist_traces.
- Manage Cloud Storage buckets and objects— List, create, delete, copy, move, upload, or download objects and buckets withstorage-mcptools.
- Inspect Storage Insights— Check insights configurations and run BigQuery queries against Storage Insights datasets withexecute_insights_query.
- Orchestrate Backup and DR operations— Create backup vaults and plans, associate resources, list backups, and trigger restores usingbackupdr-mcptools.

The gcloudModel 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:

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 arehere.

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

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 aGemini CLI extension. for the current user, making it available for all your projects.

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

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

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]"] }

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

- Claude Desktop:OpenClaude > Settings > Developer > Edit Configand editclaude_desktop_config.json.
- Cline:Click the MCP Servers icon, thenConfigure MCP Serversto editcline_mcp_settings.json.
- Cursor:Edit.cursor/mcp.jsonfor a single project or~/.cursor/mcp.jsonfor all projects.
- Gemini CLI (Manual Setup):If not using extensions, edit.gemini/settings.jsonfor a single project or~/.gemini/settings.jsonfor 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"] }, }

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

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 canauthorize as a service account using impersonationand assign the service account arole 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. Seeherefor the list of denied commands.

- 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

We welcome contributions! Whether you're fixing bugs, sharing feedback, or improving documentation, your contributions are welcome. Please read ourContributing Guideto get started.

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 underGoogle Cloud Terms of Service. It may break when the MCP specification, other SDKs, or when other solutions and products change. See also ourSecurity Policy.

Agent-ready global image CDN that AI agents can install and operate through MCP.