MCP server to deploy code to Google Cloud Run

@GoogleCloudPlatform

Repository

Basic information

About MCP server to deploy code to Google Cloud Run

MCP server to deploy apps to Cloud Run

#mcp #google-cloud#google-cloud-run#mcp-server

MCP server to deploy code to Google Cloud Run config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "cloud-run-mcp": {
      "command": "node",
      "args": [
        "mcp-server.js"
      ]
    }
  }
}

MCP server to deploy code to Google Cloud Run tools

Deploys files to Cloud Run by providing their contents directly.

Lists Cloud Run services in a given project and region.

Gets details for a specific Cloud Run service.

Gets Logs and Error Messages for a specific Cloud Run service.

folder`\*: Deploys a local folder to a Google Cloud Run service.

projects`\*: Lists available GCP projects.

project`\*: Creates a new GCP project and attach it to the first available billing account. A project ID can be optionally specified.

Overview

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: deploy and logs using 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

Frequently asked questions

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

Comments

More Developer Tools MCP servers

GripForge

gripforgeai

The tools your AI needs to make your games. Turn prompts into production-ready game assets — animated characters with their weapons attached, seamless textures, terrain, VFX, HUDs — and playable game kits Unity, Godot, U

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Moxie Docs

Jackalope-Dev

Automated codebase documentation for GitHub: searchable docs, MCP context for AI agents, doc drift detection, and Friday Cleanup PRs.

Apiosk

obcraft

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.