Google Cloud Run MCP Server

Official MCP Server to deploy to Google Cloud Run.

Local serverstdio

What is the Google Cloud Run MCP server?

Official MCP Server to deploy to Google Cloud Run. Exposed over MCP by the google cloud run mcp server, that capability becomes something an assistant can invoke while it works, not something you go and do afterwards.

What it actually does

Enable MCP-compatible AI agents to deploy apps to Cloud Run.

Its toolset

Everything the assistant can do here goes through one of these:

  • 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
  • list — projects*: Lists available GCP projects
  • create — project*: Creates a new GCP project and attach it to the first available billing account. A project ID can be optionally specified

Adding it to your client

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

Configuration

You will need 8 environment variables: GOOGLE_CLOUD_PROJECT, GOOGLE_CLOUD_REGION, DEFAULT_SERVICE_NAME, GOOGLE_APPLICATION_CREDENTIALS, PROJECT_REGION, YOUR_PROJECT_ID, PROJECT_ID, OAUTH_CLIENT_ID. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of cloud and infrastructure servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Google Cloud Run's toolset — deploy-file-contents, list-services, get-service and 4 more — is a fair guide to whether it matches your workflow.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the google cloud run mcp server does with a few real requests.

Available tools

ToolWhat it does
deploy-file-contentsDeploys files to Cloud Run by providing their contents directly.
list-servicesLists Cloud Run services in a given project and region.
get-serviceGets details for a specific Cloud Run service.
get-service-logGets Logs and Error Messages for a specific Cloud Run service.
deploy-localfolder\*: Deploys a local folder to a Google Cloud Run service.
listprojects\*: Lists available GCP projects.
createproject\*: Creates a new GCP project and attach it to the first available billing account. A project ID can be optionally specified.

How to install the Google Cloud Run MCP server

"mcpServers":{
  "cloud-run": {
    "command": "npx",
    "args": ["-y", "@google-cloud/cloud-run-mcp"]
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

VariableDescriptionRequired
GOOGLE_CLOUD_PROJECTConfiguration value read at startup.Optional
GOOGLE_CLOUD_REGIONConfiguration value read at startup.Optional
DEFAULT_SERVICE_NAMEConfiguration value read at startup.Optional
GOOGLE_APPLICATION_CREDENTIALSConfiguration value read at startup.Optional
PROJECT_REGIONConfiguration value read at startup.Optional
YOUR_PROJECT_IDConfiguration value read at startup.Optional
PROJECT_IDConfiguration value read at startup.Optional
OAUTH_CLIENT_IDConfiguration value read at startup.Optional

Example prompts to try

  • Use Google Cloud Run to deploy-file-contents.
  • Use Google Cloud Run to list-services.
  • Use Google Cloud Run to get-service.

Frequently asked questions

It connects Google Cloud Run to MCP-compatible AI assistants such as Claude and Cursor, exposing 7 tools (deploy-file-contents, list-services, get-service, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Google Cloud Run directly.