create_project
Creates a new GCP project and attempts to attach it to the first available billing account. A project ID can be optionally specified; otherwise it will be automatically generated.
LABSCO SUMMARY
It closes the loop between code the model just wrote and a URL you can open.
deploy_file_contents is what separates this from a CLI wrapper: files that exist only in the conversation go straight to Cloud Run without being written to disk first. get_service_log sits in the same surface, so a deploy that fails is diagnosed in the same turn it failed.
What it is
Google's own Cloud Run MCP server, eight tools: list and create GCP projects, list and inspect Cloud Run services, read their logs, and deploy from a local folder, from file contents passed in the conversation, or from a container image URL.
What you get
- Deploy three ways — a local folder by absolute path (deploy_local_folder), files whose contents exist only in the current conversation (deploy_file_contents), or an existing image (deploy_container_image).
- See what is running: list_services for a project, get_service for one service's details.
- Read logs and error messages for a service without leaving the session (get_service_log).
- List the GCP projects available, or create one and attach it to the first available billing account (list_projects, create_project).
Requirements
A Google Cloud account, with the project and billing you intend to deploy into, the Google Cloud SDK signed in with gcloud auth login and gcloud auth application-default login, and Node.js on the machine. Apache-2.0.
Setup effort
Follow the published steps — gcloud auth login
USE CASES
01
Getting something the model just wrote onto a real URL
Deploy the files straight out of the conversation and check the service that comes back.
02
Shipping the project you have open
Point the deploy at the folder on disk and see it alongside the services already there.
03
Finding out why a service is returning errors
Read the logs and the service configuration together instead of switching to the console.
04
Setting up a fresh project to deploy into
Create the project, attach billing, and put an image on it.
8 tools
Counted once with only startup setup. Other versions, modes or optional credentials may expose a different list.
deploy_container_image
Deploys a container image to Cloud Run. Use this tool if the user provides a container image URL.
deploy_file_contents
Deploy files to Cloud Run by providing their contents directly. Takes an array of file objects containing filename and content. Use this tool if the files only exist in the current chat context.
deploy_local_folder
Deploy a local folder to Cloud Run. Takes an absolute folder path from the local filesystem that will be deployed. Use this tool if the entire folder content needs to be deployed.
get_service
Gets details for a specific Cloud Run service.
get_service_log
Gets Logs and Error Messages for a specific Cloud Run service.
list_projects
Lists available GCP projects
list_services
Lists all Cloud Run services in a given project.
BEFORE YOU INSTALL
What to know first
Tools you get
8 tools when we connected. The server uses underscores (list_services), not the hyphenated names in the documentation. deploy_local_folder, list_projects and create_project work only when running locally, so a remote deployment on Cloud Run gets five tools.
Requires
- npx on PATH
- the Google Cloud SDK (gcloud), signed in with gcloud auth login and gcloud auth application-default login
CONTEXT COST
Light Standing cost
Rated by the size of the 8 tool definitions that ride along on every turn, not by how many there are
INSTALLATION
Connect your client
Server setup
Install the Google Cloud SDK (https://cloud.google.com/sdk/docs/install) and authenticate with your Google account.
TERMINAL
gcloud auth login
gcloud auth application-default loginMCP Clients
Gemini CLI
GEMINI CLI · TERMINAL
gemini extensions install https://github.com/GoogleCloudPlatform/cloud-run-mcpCursor, Windsurf, Antigravity, Claude Desktop
JSON
{
"mcpServers": {
"cloud-run": {
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
]
}
}
}VS Code
VS CODE · JSON
{
"servers": {
"cloud-run": {
"command": "npx",
"args": [
"-y",
"@google-cloud/cloud-run-mcp"
]
}
}
}
