Google Cloud MCP Server

@krzko

リポジトリ

基本情報

カテゴリ

クラウドとインフラ

トランスポート

stdio

作者

krzko

Google Cloud MCP Server について

🤖 A Model Context Protocol (MCP) server for Google Cloud

#google #mcp #gcp #google-cloud#google-cloud-platform#llmops #mcp-server

Google Cloud MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "google-cloud-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@modelcontextprotocol/inspector",
        "node",
        "dist/index.js"
      ]
    }
  }
}

Google Cloud MCP Server のツール

ツール一覧はまだありません

この掲載には表示できるツール一覧がまだありません。サーバーにツールがないという意味ではありません。対応機能はプロジェクトのドキュメントをご確認ください。

上のボタンで一時的なサンドボックスでこのサーバーを実行し、ツール一覧を取得できます。

概要

What is Google Cloud MCP Server?

A Model Context Protocol server that connects to Google Cloud services to provide context and tools for interacting with your Google Cloud resources. It currently supports Google Cloud Logging, Google Cloud Monitoring, and Google Cloud Spanner.

How to use Google Cloud MCP Server?

Clone the repository, install dependencies with pnpm install, and build with pnpm build. Authenticate via gcloud auth application-default login, then configure the mcpServers entry in your client with the path to the built index.js and set GOOGLE_APPLICATION_CREDENTIALS or GOOGLE_CLIENT_EMAIL/GOOGLE_PRIVATE_KEY for authentication. Start the server with pnpm start.

Key features of Google Cloud MCP Server

Query and filter log entries from Google Cloud Logging
Execute SQL queries against Spanner databases
List available databases and tables in Spanner
Query metrics with custom filters from Google Cloud Monitoring
Visualise metric data over time from Monitoring
List available metric types from Monitoring

Use cases of Google Cloud MCP Server

Retrieve and analyze logs within specific time ranges from Google Cloud Logging
Explore database schema and run SQL queries on Cloud Spanner
Monitor cloud infrastructure by querying metrics and viewing trends
Diagnose issues by correlating logs and monitoring data
Automate Google Cloud resource inspection via natural language agent tools

よくある質問

How do I authenticate with Google Cloud?

The server supports two methods: set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to a service account key file path, or set `GOOGLE_CLIENT_EMAIL` and `GOOGLE_PRIVATE_KEY` directly. It can also use `GOOGLE_CLOUD_PROJECT` if set.

What Google Cloud services are supported?

Currently supported: Google Cloud Logging, Google Cloud Monitoring, and Google Cloud Spanner. Services in development include Trace, IAM, Compute, Run, and Storage.

Why does the server timeout during initialization with Smithery?

Timeouts may occur due to authentication delays. Enable `lazyAuth: true` and set `debug: true` in your configuration to defer authentication until needed. Authentication is still required for operation.

What runtime dependencies are needed?

Node.js and pnpm are required to build and run the server. The server uses the Model Context Protocol and Google Cloud client libraries.

Can I use environment variables for authentication?

Yes, set `GOOGLE_CLIENT_EMAIL` and `GOOGLE_PRIVATE_KEY` environment variables instead of a key file. This is useful in environments where storing a key file is impractical.

「クラウドとインフラ」の他のコンテンツ

Terraform MCP Server

hashicorp

The Terraform MCP Server provides seamless integration with Terraform ecosystem, enabling advanced automation and interaction capabilities for Infrastructure as Code (IaC) development.

1.5K

Kilo IoT Platform

Kilo IoT

Your AI can finally reach the physical world. Kilo is an AI-first IoT platform for commercial and industrial operations, and this connector hands a live deployment to the AI client you already use. Not an export. Not a