Skip to content
AI Dev Toolkit.
Esc
  • AI Token CounterCount tokens for GPT, Claude, Gemini, DeepSeek, Qwen and more.Tool
  • LLM API Cost CalculatorEstimate per-request, daily and monthly API costs.Tool
  • AI Model ComparisonCompare prices, context windows and features across models.Tool
  • AI Model Pricing PagesSpecs, real costs and cheaper alternatives for popular models.Tool
  • Context Window CheckerSee whether your text fits each model’s context window.Tool
  • Subscription vs API CalculatorFind out whether a chat plan or the API is cheaper for you.Tool
  • GPU / VRAM CalculatorCheck how much VRAM a local model needs and which GPUs fit.Tool
  • Prompt Caching CalculatorEstimate savings from prompt caching.Tool

MCP server · Cloud and DevOps

Cloud Run MCP server

Lets an assistant deploy code or a local folder to Google Cloud Run, list services, read service logs and create Google Cloud projects.

Maintainer
Google Cloud (official)
Licence
Apache-2.0
Runs
Locally (npx)
Sign-in
OAuth sign-in in the app
Last activity
2026-10-08

Overview

What it does

Cloud Run MCP is Google Cloud’s server for deploying apps to Cloud Run from an AI agent. The recommended setup runs it locally with npx (@google-cloud/cloud-run-mcp) and your local Google Cloud credentials, set up with gcloud auth login and gcloud auth application-default login. Optional environment variables set a default project, region and service name. It can also run in Docker, or on Cloud Run itself behind IAM authentication, reached through gcloud run services proxy.

The tools deploy files by content or deploy a whole local folder, list and describe services, and fetch service logs and errors. When run locally it can also list projects and create a new project linked to your first billing account. Two prompts, deploy and logs, act on the current directory. It suits developers who want an agent to ship a prototype to a public URL without writing deployment config by hand. Note that by default it skips IAM checks so deployed services are public.

Tools

What the assistant can do

  • deploy-file-contents: deploy files to Cloud Run from their contents
  • deploy-local-folder: deploy a local folder (local mode only)
  • list-services and get-service: list and describe Cloud Run services
  • get-service-log: read logs and error messages for a service
  • list-projects and create-project: list or create Google Cloud projects (local mode only)
  • deploy and logs prompts for the current directory

Install

Install Cloud Run MCP server in your app

You need:

  • Node.js (LTS)
  • Google Cloud SDK, signed in with gcloud auth login and gcloud auth application-default login
  • A Google Cloud project with billing

Run in your project. --scope local keeps the servers private to you in this project; use user for every project.

Terminal
claude mcp add --scope local cloud-run -- npx -y @google-cloud/cloud-run-mcp
Native Windows (PowerShell)
claude mcp add --scope local cloud-run -- cmd /c npx -y '@google-cloud/cloud-run-mcp'

Want it alongside other servers? Open Cloud Run MCP in the MCP config generator and add the rest; it writes one file per app. The snippets follow the setup in the server’s README, checked on 2026-10-14.

Before you install

  • It deploys with your Google Cloud credentials, and create-project can attach a new project to your billing account.
  • SKIP_IAM_CHECK is true by default, which makes deployed services public; set it to false to keep IAM checks.
  • Never expose the remote (self-hosted) mode without IAM authentication; the README warns against it.
  • A local MCP server runs with your user account’s permissions. Install it only from the source linked above. See how to choose a safe server.

Why it’s listed

Why we list it

Google Cloud’s own deployment server, actively released, and the shortest path from an agent’s code to a running Cloud Run URL.

Related

All MCP serversMCP config generatorGuide: MCP servers in Claude CodeGuide: what is MCP?