The Gemini Cloud Assist MCP server connects MCP clients to the Gemini Cloud Assist APIs, enabling users to manage and troubleshoot their Google Cloud environment using natural language commands.
From the registry: MCP Server for understanding, managing & troubleshooting your GCP environment.
$ gcloud auth application-default loginPlease install the `gemini-cloud-assist-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Node.js 20+** — Requires Node.js 20 or later
- **Google Cloud SDK** — Install gcloud CLI (https://cloud.google.com/sdk/docs/install)
- **Google Cloud project + IAM roles** — roles/serviceusage.serviceUsageAdmin and roles/geminicloudassist.user
- **Application Default Credentials** — Set up ADC for the server to authenticate Run: `gcloud auth application-default login`
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@google-cloud/gemini-cloud-assist-mcp@0.2.0"]
Note: Google Cloud Assist investigations from natural language. Note: Google is migrating to a Remote MCP architecture; pin to 0.2.0 for legacy local server.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.All Azure MCP tools to create a seamless connection between AI agents and Azure services.