GoogleCloudPlatform/cloud-run-mcp

MCP server to deploy apps to Cloud Run

What it solves

This project provides a Model Context Protocol (MCP) server that allows AI agents to interact with Google Cloud Run. It eliminates the manual process of deploying and managing Cloud Run services by enabling AI-powered IDEs, CLI agents, and assistant apps to perform these tasks directly.

How it works

The server acts as a bridge between an MCP-compatible AI agent (such as Claude Desktop, Cursor, or Gemini CLI) and the Google Cloud Platform (GCP). It exposes a set of tools and prompts that the agent can call to execute GCP actions. It can be run locally via Node.js or Docker, or hosted remotely on Cloud Run itself.

Who it’s for

Developers using AI-assisted coding tools and agents that support the Model Context Protocol to automate their deployment pipeline to Google Cloud Run.

Highlights

  • Deployment Tools: Includes tools to deploy file contents or local folders directly to Cloud Run.
  • Service Management: Ability to list services, get specific service details, and and retrieve logs and error messages.
  • Project Management: Tools to create new GCP projects and list available projects (available when running locally).
  • Flexible Hosting: Supports local execution (Node.js/Docker) or remote hosting on Cloud Run with IAM authentication.
  • Gemini CLI Integration: Can be installed as a direct extension for the Gemini CLI.
  • OAuth Support: Supports OAuth authentication for secure access to Google Cloud resources.

Related

  • Project
  • Project
  • Project
  • Project
  • Project