MCP server to deploy code to Google Cloud Run
@GoogleCloudPlatform
MCP server to deploy apps to Cloud Run
概要
What is Cloud Run MCP server and Gemini CLI extension?
Enable MCP-compatible AI agents to deploy apps to Cloud Run. It integrates with Google Cloud Run and can be used with Gemini CLI, AI-powered IDEs, assistant apps, and agent SDKs like Google Gen AI SDK and Agent Development Kit.
How to use Cloud Run MCP server and Gemini CLI extension?
Install via npx: npx -y @google-cloud/cloud-run-mcp. Configure in your MCP client’s config file as a local server (using Node.js or Docker) or as a remote server deployed on Cloud Run with IAM authentication. Can also be installed as a Gemini CLI extension using gemini extensions install. Set environment variables for default project, region, and service name.
Key features of Cloud Run MCP server and Gemini CLI extension
- Tools:
deploy-file-contents,list-services,get-service,get-service-log - Prompts:
deployandlogsusing current directory or default service name - Deploy local folders and manage GCP projects (local only)
- Supports both local and remote (Cloud Run-hosted) execution
- OAuth authentication for Gemini CLI
- Configurable via environment variables for defaults and security
Use cases of Cloud Run MCP server and Gemini CLI extension
- Deploy code from an AI chat window to Cloud Run in one step
- List and inspect existing Cloud Run services via natural language
- Retrieve service logs for debugging from an AI-powered IDE
- Create new GCP projects and deploy apps from agent SDKs
- Integrate with multi‑agent workflows using MCP‑compatible tools
FAQ from Cloud Run MCP server and Gemini CLI extension
What tools are provided?
deploy-file-contents, list-services, get-service, get-service-log. Local tools include deploy-local-folder, list-projects, and create-project.
How do I authenticate?
For local use: gcloud auth login and gcloud auth application-default login. For remote server: IAM authentication via Cloud Run proxy. For Gemini CLI: OAuth supported.
Can I run the server remotely?
Yes. Deploy the MCP server itself to Cloud Run (unauthenticated by default, secure via IAM) and connect using gcloud run services proxy on a local port.
What environment variables can I set?
`GOOGLE_CLOUD