Cloud Run MCP

Enable MCP-compatible AI agents to deploy apps to Google Cloud Run. Deploy from AI-powered IDEs, CLI agents, or assistant apps.

Tools

• deploy-file-contents: Deploys files to Cloud Run by providing their contents directly
• list-services: Lists Cloud Run services in a given project and region
• get-service: Gets details for a specific Cloud Run service
• get-service-log: Gets logs and error messages for a specific Cloud Run service
• deploy-local-folder: Deploys a local folder to a Google Cloud Run service (local only)
• list-projects: Lists available GCP projects (local only)
• create-project: Creates a new GCP project and attaches it to the first available billing account (local only)

Prompts

• deploy: Deploys the current working directory to Cloud Run
• logs: Gets the logs for a Cloud Run service

Setup

Prerequisites

1. Install the Google Cloud SDK
2. Authenticate: gcloud auth login
3. Set up application credentials: gcloud auth application-default login

Local Configuration (Recommended)

Run the server locally using your Google Cloud credentials:

"cloud-run": {
  "command": "npx",
  "args": ["-y", "@google-cloud/cloud-run-mcp"],
  "env": {
    "GOOGLE_CLOUD_PROJECT": "your-project-id",
    "GOOGLE_CLOUD_REGION": "us-central1",
    "DEFAULT_SERVICE_NAME": "my-service"
  }
}

Remote Configuration

Deploy the MCP server itself to Cloud Run:

gcloud run deploy cloud-run-mcp \
  --image us-docker.pkg.dev/cloudrun/container/mcp \
  --no-allow-unauthenticated

Then run a local proxy:

gcloud run services proxy cloud-run-mcp --port=3000 --region=REGION

OAuth Support

The server supports OAuth authentication. Use the provided .env.gcloud-sdk-oauth template for Google Cloud SDK OAuth client configuration.

Cloud Run Skills

Also includes Cloud Run skills based on gcloud CLI, enabling agents to perform all Cloud Run actions available through gcloud.