Google Cloud Run MCP server for AI agents

This MCP server enables AI agents to deploy applications to Google Cloud Run, providing a bridge between AI-powered development environments and Google Cloud services. It offers tools for deploying code, managing services, and interacting with Google Cloud resources.

Installation Options

Local Installation

Setting up the Cloud Run MCP server on your local machine allows you to use your local Google Cloud credentials, ideal for AI-assisted IDEs or desktop AI applications.

Install prerequisites:
- Node.js (LTS version recommended)
- Google Cloud SDK
Authenticate with Google Cloud:
```
gcloud auth login
```
Set up application credentials:
```
gcloud auth application-default login
```

Configure your MCP client by adding the following to your MCP configuration file:

"cloud-run": {
  "command": "npx",
  "args": ["-y", "https://github.com/GoogleCloudPlatform/cloud-run-mcp"]
}

Remote Installation

Running the MCP server on Cloud Run with IAM authentication provides a secure connection from your local machine. Note that with this option, you can only deploy code to the same Google Cloud project where the MCP server is running.

Install and authenticate with the Google Cloud SDK:
```
gcloud auth login
```

Set your Google Cloud project:

gcloud config set project YOUR_PROJECT_ID

Deploy the MCP server to Cloud Run:

gcloud run deploy cloud-run-mcp --image us-docker.pkg.dev/cloudrun/container/mcp --no-allow-unauthenticated

When prompted, select a region (e.g., europe-west1).

Create a local proxy to connect securely to the remote MCP server:

gcloud run services proxy cloud-run-mcp --port=3000 --region=REGION --project=PROJECT_ID

Update your MCP client configuration:

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

Alternatively, if your MCP client doesn't support the url attribute, use:

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

Available Tools

Deployment Tools

deploy-file-contents: Deploy files to Cloud Run by providing their contents directly
deploy-local-files: Deploy files from your local system to Cloud Run (local installation only)
deploy-local-folder: Deploy an entire local folder to Cloud Run (local installation only)

Service Management

list-services: List all Cloud Run services in a project and region
get-service: Get detailed information about a specific Cloud Run service
get-service-log: Retrieve logs and error messages for a Cloud Run service

Project Management

list-projects: List available Google Cloud projects (local installation only)
create-project: Create a new GCP project with billing account attachment (local installation only)

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "cloud-run" '{"command":"npx","args":["-y","https://github.com/GoogleCloudPlatform/cloud-run-mcp"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cloud-run": {
            "command": "npx",
            "args": [
                "-y",
                "https://github.com/GoogleCloudPlatform/cloud-run-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "cloud-run": {
            "command": "npx",
            "args": [
                "-y",
                "https://github.com/GoogleCloudPlatform/cloud-run-mcp"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect