Cloud Run MCP Server

What is Cloud Run MCP Server about?

The server enables MCP‑compatible AI agents and developers to deploy code, manage services, and retrieve logs on Google Cloud Run without manual gcloud commands.

How to use Cloud Run MCP Server?

Install the server locally via Node.js (preferred) or Docker.
Configure your MCP client with the provided npx command and optional environment variables (project, region, default service name).
Run the server (local or remote) and interact through Gemini CLI, IDE extensions, or custom agents using built‑in tools and natural‑language prompts such as deploy and logs.
For remote usage, deploy the server to Cloud Run, enable IAM authentication, and proxy locally to the SSE endpoint.

Key features of Cloud Run MCP Server

Toolset: Deploy files/folders, list services, create projects, fetch logs, and get service details.
Prompts: Ready‑made natural‑language shortcuts (deploy, logs).
Multi‑environment support: Run locally via Node.js or Docker, or host remotely on Cloud Run with secure IAM proxy.
Gemini CLI extension: Install with a single script to use from Gemini‑compatible CLIs.
Environment variables: Pre‑configure project, region, and default service name for seamless operations.

Use cases of Cloud Run MCP Server

AI‑assisted development: IDEs like Cursor can invoke deployment commands automatically.
Automated CI/CD: Trigger deployments from Gemini CLI or custom agents without writing gcloud scripts.
Rapid prototyping: Spin up a temporary Cloud Run service from local code with a single prompt.
Managed project creation: Create new GCP projects and attach billing via the create-project tool.

FAQ from the Cloud Run MCP Server

Q: Do I need to install the Google Cloud SDK? A: Yes, for authentication and for remote deployment scenarios.

Q: Can I run the server without Docker? A: Absolutely; the Node.js npx approach is the recommended and most convenient method.

Q: Is the remote server publicly accessible? A: No. The remote deployment uses IAM authentication and should be deployed with --no-allow-unauthenticated.

Q: How do I set default service names? A: Add DEFAULT_SERVICE_NAME to the env section of the MCP configuration.

Q: What if I need custom environment variables? A: Include them in the env object of the server configuration.

MCP server to deploy code to Google Cloud Run

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

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

Deploy from Gemini CLI and other AI-powered CLI agents:

Deploy from AI-powered IDEs:

Deploy from AI assistant apps:

Deploy from agent SDKs, like the Google Gen AI SDK or Agent Development Kit.

[!NOTE]
This is the repository of an MCP server to deploy code to Cloud Run, to learn how to host MCP servers on Cloud Run, visit the Cloud Run documentation.

Tools

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-files*: Deploys files from the local file system to a Google 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.

* only available when running locally

Prompts

Prompts are natural language commands that can be used to perform common tasks. They are shortcuts for executing tool calls with pre-filled arguments.

deploy: Deploys the current working directory to Cloud Run. If a service name is not provided, it will use the DEFAULT_SERVICE_NAME environment variable, or the name of the current working directory.
logs: Gets the logs for a Cloud Run service. If a service name is not provided, it will use the DEFAULT_SERVICE_NAME environment variable, or the name of the current working directory.

Use as a Gemini CLI extension

To install this as a Gemini CLI extension, run the following command:

mkdir -p ~/.gemini/extensions/cloud-run/gemini-extension && \
  curl -s -L https://raw.githubusercontent.com/GoogleCloudPlatform/cloud-run-mcp/main/gemini-extension.json > ~/.gemini/extensions/cloud-run/gemini-extension.json && \
  curl -s -L https://raw.githubusercontent.com/GoogleCloudPlatform/cloud-run-mcp/main/gemini-extension/GEMINI.md > ~/.gemini/extensions/cloud-run/gemini-extension/GEMINI.md

Use as local MCP server

Run the Cloud Run MCP server on your local machine using local Google Cloud credentials. This is best if you are using an AI-assisted IDE (e.g. Cursor) or a desktop AI application (e.g. Claude).

Install the Google Cloud SDK and authenticate with your Google account.
Log in to your Google Cloud account using the command:
```
gcloud auth login
```
Set up application credentials using the command:
```
gcloud auth application-default login
```

Then configure the MCP server using either Node.js or Docker:

Using Node.js

Install Node.js (LTS version recommended).

Update the MCP configuration file of your MCP client with the following:

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

[Optional] Add default configurations

   "cloud-run": {
      "command": "npx",
      "args": ["-y", "@google-cloud/cloud-run-mcp"],
      "env": {
            "GOOGLE_CLOUD_PROJECT": "PROJECT_NAME",
            "GOOGLE_CLOUD_REGION": "PROJECT_REGION",
            "DEFAULT_SERVICE_NAME": "SERVICE_NAME"
      }
   }

Using Docker

See Docker's MCP catalog, or use these manual instructions:

Install Docker

Update the MCP configuration file of your MCP client with the following:

   "cloud-run": {
     "command": "docker",
     "args": [
       "run",
       "-i",
       "--rm",
       "-e",
       "GOOGLE_APPLICATION_CREDENTIALS",
       "-v",
       "/local-directory:/local-directory",
       "mcp/cloud-run-mcp:latest"
     ],
     "env": {
       "GOOGLE_APPLICATION_CREDENTIALS": "/Users/slim/.config/gcloud/application_default-credentials.json",
       "DEFAULT_SERVICE_NAME": "SERVICE_NAME"
     }
   }

Use as remote MCP server

[!WARNING]
Do not use the remote MCP server without authentication. In the following instructions, we will use IAM authentication to secure the connection to the MCP server from your local machine. This is important to prevent unauthorized access to your Google Cloud resources.

Run the Cloud Run MCP server itself on Cloud Run with connection from your local machine authenticated via IAM. With this option, you will only be able to deploy code to the same Google Cloud project as where the MCP server is running.

Install the Google Cloud SDK and authenticate with your Google account.
Log in to your Google Cloud account using the command:
```
gcloud auth login
```
Set your Google Cloud project ID using the command:
```
gcloud config set project YOUR_PROJECT_ID
```
Deploy the Cloud Run MCP server to Cloud Run:
```
gcloud run deploy cloud-run-mcp --image us-docker.pkg.dev/cloudrun/container/mcp --no-allow-unauthenticated
```
When prompted, pick a region, for example europe-west1.

Note that the MCP server is not publicly accessible, it requires authentication via IAM.

[Optional] Add default configurations

gcloud run services update cloud-run-mcp --region=REGION --update-env-vars GOOGLE_CLOUD_PROJECT=PROJECT_NAME,GOOGLE_CLOUD_REGION=PROJECT_REGION,DEFAULT_SERVICE_NAME=SERVICE_NAME,SKIP_IAM_CHECK=false

Run a Cloud Run proxy on your local machine to connect securely using your identity to the remote MCP server running on Cloud Run:
```
gcloud run services proxy cloud-run-mcp --port=3000 --region=REGION --project=PROJECT_ID
```
This will create a local proxy on port 3000 that forwards requests to the remote MCP server and injects your identity.

Update the MCP configuration file of your MCP client with the following:

   "cloud-run": {
     "url": "http://localhost:3000/sse"
   }

If your MCP client does not support the url attribute, you can use mcp-remote:

   "cloud-run": {
     "command": "npx",
     "args": ["-y", "mcp-remote", "http://localhost:3000/sse"]
   }