Google Cloud MCP

🚀 Google Cloud MCP Server

A Model Context Protocol (MCP) server that connects to Google Cloud services to provide context and tools for interacting with your Google Cloud resources.

🚀 Quick Start

The Google Cloud MCP Server is a Model Context Protocol server that connects to Google Cloud services. It offers various features for interacting with different Google Cloud resources.

✨ Features

Supported Services

• Supported Services:
  • [x] Google Cloud Logging
  • [x] Google Cloud Monitoring
  • [x] Google Cloud Spanner
• Services in Development:
  • [ ] Google Cloud Trace
  • [ ] Google IAM
  • [ ] Google Cloud Compute
  • [ ] Google Cloud Run
  • [ ] Google Cloud Storage

Google Cloud Logging

Query and filter log entries from Google Cloud Logging:

• Query logs using custom filters.
• Search for logs within a specific time range.
• Display log entries in a readable format.

Google Cloud Spanner

Interact with Google Cloud Spanner databases:

• Execute SQL queries on Spanner databases.
• List available databases and tables.
• Explore database schemas.

Google Cloud Monitoring

Retrieve and analyze metric data from Google Cloud Monitoring:

• Query metrics using custom filters.
• Visualize metric data over time.
• List available metric types.

Google Cloud Trace

Analyze distributed traces from Google Cloud Trace:

• Get a trace by ID.
• List recent traces with filtering options.
• Find traces associated with logs.
• Identify failed traces.
• Query traces using natural language (e.g., "Show failed traces in the past hour").

🔧 Technical Details

Authentication

This server supports two methods for authenticating with Google Cloud:

1. Service Account Key File (recommended): Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account key file. This is the standard authentication method for Google Cloud.
2. Environment Variables: Set the GOOGLE_CLIENT_EMAIL and GOOGLE_PRIVATE_KEY environment variables directly. This is useful in environments where you cannot store key files.

The server will also use the GOOGLE_CLOUD_PROJECT environment variable if it is set; otherwise, it will try to determine the project ID from the authentication credentials.

📦 Installation

# Clone the repository
git clone https://github.com/krzko/google-cloud-mcp.git
cd google-cloud-mcp

# Install dependencies
pnpm install

# Build
pnpm build

Authenticate with Google Cloud:

gcloud auth application-default login

Configure mcpServers in your client:

{
  "mcpServers": {
      "google-cloud-mcp": {
          "command": "node",
          "args": [
              "/Users/foo/code/google-cloud-mcp/dist/index.js"
          ],
          "env": {
              "GOOGLE_APPLICATION_CREDENTIALS": "/Users/foo/.config/gcloud/application_default_credentials.json"
          }
      }
  }
}

💻 Usage Examples

Development

Start the Server

# Build the project
pnpm build

# Start the server
pnpm start

Development Mode

# Build the project
pnpm build

# Start the server and the inspector tool
npx -y @modelcontextprotocol/inspector node dist/index.js

Troubleshooting

Server Timeout Issues

If you encounter timeout issues when running the server with Smithery, try the following steps:

1. Enable debug logging by setting debug: true in your configuration.
2. Ensure lazyAuth: true is set to defer authentication until it is actually needed.
3. Make sure your credential file is accessible and in the correct format.
4. Check the logs for any error messages.

⚠️ Important Note

Authentication is still required for operation, but with lazy loading enabled, the server will start immediately and authenticate when needed, rather than during initialization.

Authentication Issues

The server supports two authentication methods:

1. Service Account Key File: Set the GOOGLE_APPLICATION_CREDENTIALS environment variable to the path of your service account key file.
2. Environment Variables: Set the GOOGLE_CLIENT_EMAIL and GOOGLE_PRIVATE_KEY environment variables correctly.

If you encounter authentication issues, ensure that:

• Your service account has the necessary permissions.
• The key file is in the correct format and is accessible.
• The environment variables are set correctly.

💡 Usage Tip

When using the Google Cloud MCP Server, make sure to configure the authentication correctly according to your environment to ensure smooth operation.