Google Cloud Logging MCP Server

Google Cloud Logging MCP Server

Enables AI assistants to query, search, and analyze logs across Google Cloud Platform projects. It supports advanced filtering by severity or resource type and provides detailed log entry retrieval and project listing capabilities.

Category
访问服务器

README

Google Cloud Logging MCP Server

A Model Context Protocol (MCP) server that provides access to Google Cloud Logging. This server allows AI assistants to query, search, and analyze logs from Google Cloud Platform projects.

Features

  • Query Logs: Search and filter logs across GCP projects
  • Get Log Details: Retrieve detailed information about specific log entries
  • List Projects: List available GCP projects

Getting Started

Prerequisites

  • Bun runtime
  • Google Cloud credentials configured
  • Access to Google Cloud Logging API

Quick Start

  1. Install dependencies:

    bun install
    
  2. Set up Google Cloud credentials:

    # Option 1: Use gcloud CLI
    gcloud auth application-default login
    
    # Option 2: Use service account
    export GOOGLE_APPLICATION_CREDENTIALS="/path/to/service-account.json"
    
  3. Set your project ID:

    export GOOGLE_CLOUD_PROJECT="your-project-id"
    
  4. Run the server:

    bun run start
    

Using with Claude Desktop

Add the following to your Claude Desktop configuration file:

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

{
  "mcpServers": {
    "cloud-logging": {
      "command": "bun",
      "args": ["run", "/path/to/cloud-logging-mcp/src/main.ts"],
      "env": {
        "GOOGLE_CLOUD_PROJECT": "your-project-id"
      }
    }
  }
}

Example Tool Usage

Query Logs

Search and filter logs from Google Cloud Logging.

{
  "tool": "queryLogs",
  "input": {
    "projectId": "my-project",
    "filter": "resource.type=\"cloud_run_revision\" AND severity>=ERROR",
    "orderBy": {
      "timestamp": "desc"
    },
    "pageSize": 50
  }
}

Parameters:

  • projectId: GCP project ID
  • filter: Log filter query (follows GCP logging query syntax)
  • orderBy: Sort order for results
  • pageSize: Number of results per page
  • pageToken: Token for pagination
  • resourceNames: Specific log resources to query
  • summaryFields: Fields to include in the summary

Get Log Detail

Retrieve complete details for a specific log entry.

{
  "tool": "getLogDetail",
  "input": {
    "projectId": "my-project",
    "logId": "65f5a7b60000000001234567"
  }
}

Parameters:

  • projectId: GCP project ID
  • logId: The unique identifier of the log entry

List Projects

List all accessible Google Cloud projects.

{
  "tool": "listProjects",
  "input": {}
}

Parameters: None

Common Filter Examples

  • By severity: severity>=ERROR
  • By time range: timestamp>="2024-01-01T00:00:00Z"
  • By resource: resource.type="cloud_run_revision"
  • By text search: textPayload:"connection timeout"
  • Combined: resource.type="k8s_container" AND severity=ERROR AND timestamp>="2024-01-01T00:00:00Z"

Troubleshooting

  1. Authentication errors: Ensure your Google Cloud credentials are properly configured
  2. Permission errors: Check that your account has the logging.logEntries.list permission
  3. No results: Verify your filter syntax and that logs exist for your query

Development

# Run tests
bun test

# Type checking
bun run typecheck

# Linting
bun run lint

# Format code
bun run format

Architecture

The server follows a clean architecture pattern:

  • /adapter: External service integrations (Google Cloud APIs)
  • /domain: Core business logic and data models
  • /port: Interface definitions and MCP tool handlers
  • /util: Utility functions and helpers

License

MIT

推荐服务器

Baidu Map

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。

官方
精选
JavaScript
Playwright MCP Server

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。

官方
精选
TypeScript
Magic Component Platform (MCP)

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。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

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。

官方
精选
本地
TypeScript
VeyraX

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。

官方
精选
本地
graphlit-mcp-server

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。

官方
精选
TypeScript
Kagi MCP Server

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。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

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。

官方
精选