Google Cloud is a Infrastructure MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent google Cloud Platform — manage Compute Engine, Cloud Storage, BigQuery, Cloud Run, and more. Install in 1 minute with mcpizy install gcp.
Infrastructure
Google Cloud Platform — manage Compute Engine, Cloud Storage, BigQuery, Cloud Run, and more.
Official homepagemcpizy install gcpnpx -y @modelcontextprotocol/server-gcplist_instancesList Compute Engine VM instances in a project
Inputs
projectstringrequiredzonestringoptionallist_bucketsList Cloud Storage buckets
Inputs
projectstringrequiredlist_objectsList objects in a bucket
Inputs
bucketstringrequiredbigquery_queryRun a BigQuery SQL query
Inputs
projectstringrequiredquerystringrequiredlist_cloud_run_servicesList Cloud Run services in a region
Inputs
projectstringrequiredregionstringrequiredread_logsRead Cloud Logging entries
Inputs
projectstringrequiredfilterstringoptionalWorks identically across clients. Only the config file path differs.
~/.claude.json{
"mcpServers": {
"gcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json",
"GCP_PROJECT_ID": "my-project"
}
}
}
}.cursor/mcp.json{
"mcpServers": {
"gcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json",
"GCP_PROJECT_ID": "my-project"
}
}
}
}~/.codeium/windsurf/mcp_config.json{
"mcpServers": {
"gcp": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-gcp"
],
"env": {
"GOOGLE_APPLICATION_CREDENTIALS": "/path/to/service-account.json",
"GCP_PROJECT_ID": "my-project"
}
}
}
}Paste any of these prompts into Claude Code, Cursor or another MCP-compatible client.
“List all Compute Engine VMs in zone us-central1-a”
Uses: list_instances
“Run a BigQuery: SELECT COUNT(*) FROM events.page_views WHERE date > CURRENT_DATE() - 7”
Uses: bigquery_query
“Show me all Cloud Run services in europe-west1 and their revision counts”
Uses: list_cloud_run_services
“Read Cloud Logging errors from the last hour in project my-project”
Uses: read_logs
If Google Cloud doesn't fit your stack, these Infrastructure MCP servers solve similar problems.
The Google Cloud MCP server is an Infrastructure Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents google Cloud Platform — manage Compute Engine, Cloud Storage, BigQuery, Cloud Run, and more. It exposes Google Cloud's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install gcp` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @modelcontextprotocol/server-gcp` and restarting Claude Code.
Yes. The Google Cloud MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Google Cloud account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can google Cloud Platform — manage Compute Engine, Cloud Storage, BigQuery, Cloud Run, and more directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Google Cloud operations, inspect results, chain Google Cloud with other MCP servers (see our Workflow Recipes), and automate repetitive infrastructure tasks without leaving your editor.