Google Cloud MCP Server
A Model Context Protocol server that connects to Google Cloud services, allowing users to query logs, interact with Spanner databases, and analyze monitoring metrics through natural language.
README
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.
Services
Supported services:
- [x] Google Cloud Logging
- [x] Google Cloud Monitoring
- [x] Google Cloud Spanner
Servers 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 with custom filters
- Search logs within specific time ranges
- Format and display log entries in a readable format
Google Cloud Spanner
Interact with Google Cloud Spanner databases:
- Execute SQL queries against Spanner databases
- List available databases and tables
- Explore database schema
Google Cloud Monitoring
Retrieve and analyse metrics from Google Cloud Monitoring:
- Query metrics with custom filters
- Visualise metric data over time
- List available metric types
Google Cloud Trace
Analyse distributed traces from Google Cloud Trace:
- Retrieve traces by ID
- List recent traces with filtering options
- Find traces associated with logs
- Identify failed traces
- Use natural language to query traces (e.g., "Show me failed traces from the last hour")
Authentication
This server supports two methods of authentication with Google Cloud:
-
Service Account Key File (Recommended): Set the
GOOGLE_APPLICATION_CREDENTIALSenvironment variable to the path of your service account key file. This is the standard Google Cloud authentication method. -
Environment Variables: Set
GOOGLE_CLIENT_EMAILandGOOGLE_PRIVATE_KEYenvironment variables directly. This is useful for environments where storing a key file is not practical.
The server will also use the GOOGLE_CLOUD_PROJECT environment variable if set, otherwise it will attempt 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 to Google Cloud:
gcloud auth application-default login
Configure the 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"
}
}
}
}
Development
Starting the server
# Build the project
pnpm build
# Start the server
pnpm start
Development mode
# Build the project
pnpm build
# Start the server and inspector
npx -y @modelcontextprotocol/inspector node dist/index.js
Using with Smithery (soon)
This server can be deployed and used with Smithery. The server implements lazy loading of authentication, which means it will start immediately and defer authentication until it's actually needed. Authentication is still required for operation, but this approach prevents timeouts during server initialization.
NOTE: Smithery local server support is currently in development and may not yet available.
Troubleshooting
Server Timeout Issues
If you encounter timeout issues when running the server with Smithery, try the following:
- Enable debug logging by setting
debug: truein your configuration - Ensure
lazyAuth: trueis set to defer authentication until it's actually needed - Ensure your credentials file is accessible and valid
- Check the logs for any error messages
Important: 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 methods of authentication:
- Service Account Key File: Set
GOOGLE_APPLICATION_CREDENTIALSenvironment variable to the path of your service account key file - Environment Variables: Set
GOOGLE_CLIENT_EMAILandGOOGLE_PRIVATE_KEYenvironment variables
If you're having authentication issues, make sure:
- Your service account has the necessary permissions
- The key file is properly formatted and accessible
- Environment variables are correctly set
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。