Arthas MCP
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.
What is Arthas MCP?
Arthas MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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.
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.
This server falls under the Developer Tools and Monitoring & Observability categories on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Arthas MCP Server is an MCP-based diagnostic toolkit for Jav
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx arthas-mcp-serverConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Arthas MCP
Arthas MCP Server is an MCP-based diagnostic toolkit that bridges Alibaba Arthas — the industry-standard Java diagnostic tool — with AI assistants, enabling LLMs to inspect and troubleshoot live Java applications through natural language. It exposes nine tools covering connection management, JVM inspection, thread and memory analysis, performance profiling, and method call tracing, all via Arthas's HTTP WebConsole API running on localhost port 8563. Developers can use it to diagnose production Java issues, profile hot methods, and understand JVM behavior without manually constructing Arthas commands.
Prerequisites
- Python 3.8 or higher with uv package manager installed
- A running Java application with Alibaba Arthas attached in either attach mode or agent mode
- Arthas HTTP WebConsole active and listening on http://localhost:8563
- An MCP-compatible client such as Claude Desktop or Cursor
Ensure Arthas is running and attached to your Java application
Start Arthas and attach it to your running Java process. The HTTP API must be enabled — by default it listens on port 8563. Verify with a browser or curl.
# Download and start Arthas (if not already installed)
curl -O https://arthas.aliyun.com/arthas-boot.jar
java -jar arthas-boot.jar --http-port 8563
# Verify the HTTP API is active
curl http://localhost:8563/apiClone the Arthas MCP Server repository and install dependencies
Clone the repository and use uv to install the Python dependencies.
git clone https://github.com/toby1123yjh/arthas_mcp_server.git
cd arthas_mcp_server
uv syncStart the MCP server
Run the main entry point. The server will connect to Arthas on localhost:8563 by default, or the URL specified in the ARTHAS_URL environment variable.
export ARTHAS_URL=http://localhost:8563
python main.pyRegister the server in your MCP client configuration
Add the Arthas MCP server to your client's configuration. For Cursor, edit ~/.cursor/mcp.json. For Claude Desktop, edit claude_desktop_config.json.
{
"mcpServers": {
"arthas-mcp": {
"command": "python",
"args": ["/absolute/path/to/arthas_mcp_server/main.py"],
"env": {
"ARTHAS_URL": "http://localhost:8563"
}
}
}
}Connect and start diagnosing
Use the connect_arthas tool through your AI assistant to establish the diagnostic session, then query JVM info, threads, memory, or trace method calls.
Arthas MCP Examples
Client configuration
Claude Desktop or Cursor configuration entry for the Arthas MCP server, pointing at a locally running Arthas WebConsole.
{
"mcpServers": {
"arthas-mcp": {
"command": "python",
"args": ["/path/to/arthas_mcp_server/main.py"],
"env": {
"ARTHAS_URL": "http://localhost:8563"
}
}
}
}Prompts to try
Use these prompts to diagnose live Java applications through Claude once the Arthas MCP server is connected.
- "Connect to Arthas and show me the current JVM information for my application"
- "What threads are running in my Java app and which ones are blocked?"
- "Show me current memory usage breakdown including heap and non-heap"
- "Trace all calls to the OrderService.processOrder method and show me the execution time"
- "Run an Arthas dashboard command and summarize the top CPU-consuming threads"Troubleshooting Arthas MCP
connect_arthas fails with connection refused error
Verify Arthas is running and the HTTP API is active: curl http://localhost:8563/api should return a JSON response. If Arthas is on a different port, update the ARTHAS_URL environment variable to match.
uv sync fails with dependency resolution errors
Ensure you are using Python 3.8 or higher. Try creating a fresh virtual environment: uv venv && source .venv/bin/activate, then re-run uv sync. For development dependencies, use uv sync --extra dev.
trace_method_calls or analyze_performance returns no data
The target Java class and method must be loaded by the JVM and actively called. Verify the fully qualified class name and method name are correct. Some methods may require enhanced bytecode injection — check the Arthas output for permission or enhancement errors.
Frequently Asked Questions about Arthas MCP
What is Arthas MCP?
Arthas MCP is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Arthas MCP?
Follow the installation instructions on the Arthas MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Arthas MCP?
Arthas MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Arthas MCP free to use?
Yes, Arthas MCP is open source and available under the MIT license. You can use it freely in both personal and commercial projects.
Arthas MCP Alternatives — Similar Developer Tools Servers
Looking for alternatives to Arthas MCP? Here are other popular developer tools servers you can use with Claude, Cursor, and VS Code.
Ecc
★ 188.2kThe agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
Javaguide
★ 155.8kJava 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Gemini CLI
★ 104.5kA secure MCP server that wraps the Google Gemini CLI, allowing clients to query Gemini models using local OAuth sessions without requiring an API key. It provides tools for model interaction and diagnostics with built-in protection against command in
Awesome MCP Servers
★ 87.3k⭐ Curated list of Model Context Protocol (MCP) servers - tools that extend Claude Desktop, Cursor, Windsurf, and other MCP clients with custom capabilities.
MCP Servers
★ 86.0kModel Context Protocol Servers
CC Switch
★ 77.5kA cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Gemini CLI & Hermes Agent. Only official website: ccswitch.io
Browse More Developer Tools MCP Servers
Explore all developer tools servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Arthas MCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use Arthas MCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.