Java 诊断 MCP 服务器

概述

Arthas MCP 服务器是一款基于 MCP 的 Java 应用诊断工具包，设计用于 LLM 集成。它与阿里巴巴 Arthas 集成，使 AI 助手能够分析和诊断 Java 应用。

特色

• 通过支持LLM的工具进行智能诊断
• 实时监控：JVM、线程、内存
• 性能分析：CPU 使用率、呼叫追踪、瓶颈
• 运行时操作：动态类/方法工具
• 例如。

快速启动

安装

跑

MCP工具

• connect_arthas：连接Arthas WebConsole
• get_connection_status：获取当前状态
• disconnect_arthas：断开连接
• get_jvm_info：JVM信息
• get_thread_info：线程状态与性能
• get_memory_info：内存使用与GC
• execute_arthas_command：运行自定义 Arthas 命令
• analyze_performance：绩效分析
• trace_method_calls：方法调用追踪

配置

添加到光标 / Claude 代码

macOS： ~/.cursor/mcp.json 窗口：C:\Users\{username}\.cursor\mcp.json

开始，阿尔萨斯

有多种部署方式：连接模式或代理模式。

Arthas MCP Server

Java diagnostics MCP server

Overview

Arthas MCP Server is an MCP-based diagnostic toolkit for Java applications, designed for LLM integration. It integrates with Alibaba Arthas so AI assistants can analyze and diagnose Java apps.

Features

• Intelligent diagnostics via LLM-friendly tools
• Real-time monitoring: JVM, threads, memory
• Performance analysis: CPU usage, call tracing, bottlenecks
• Runtime operations: dynamic class/method tools
• exmaple

Quick Start

Install

uv sync

Run

python main.py

MCP Tools

• connect_arthas: connect to Arthas WebConsole
• get_connection_status: get current status
• disconnect_arthas: disconnect
• get_jvm_info: JVM info
• get_thread_info: thread status and performance
• get_memory_info: memory usage and GC
• execute_arthas_command: run custom Arthas command
• analyze_performance: performance analysis
• trace_method_calls: method call tracing

Config

Add to Cursor / Claude Code

macOS: ~/.cursor/mcp.json Windows: C:\Users\{username}\.cursor\mcp.json

{
  "mcpServers": {
    "arthas": {
      "command": "uv",
      "args": ["--directory", "F:\\path\\to\\arthas_mcp_server", "run", "python", "main.py"],
      "env": { "ARTHAS_URL": "http://localhost:8563" }
    }
  }
}

Start Arthas

There are multiple deployment methods: either attach mode or agent mode. Both approaches ultimately result in listening for HTTP requests (Arthas commands) on port 8563.

Project Structure

arthas_mcp_server/
├── src/
│   ├── __init__.py
│   ├── models.py
│   ├── server.py
│   └── client.py
├── main.py
├── pyproject.toml
└── README.md

Development

uv sync --extra dev