Jvm MCP Server

🚀 JVM MCP Server

A JVM monitoring MCP server implemented based on Arthas, offering a simple and easy - to - use Python interface for monitoring and analyzing Java processes.

🚀 Quick Start

Start the Server

1. Use uv to run the server:

# Start in local mode
uv run jvm-mcp-server

# Run with an environment variable file (if remote connection is configured)
uv run --env-file .env jvm-mcp-server

# Run in a specific directory (if needed)
uv --directory /path/to/project run --env-file .env jvm-mcp-server

2. Use in Python code:

from jvm_mcp_server import JvmMcpServer

server = JvmMcpServer()
server.run()

3. Use the MCP tool: Example configuration file:

{
    "mcpServers": {
      "jvm-mcp-server": {
        "command": "uv",
        "args": [
          "--directory",
          "/path/to/jvm-mcp-server",
          "run",
          "--env-file",
          "/path/to/jvm-mcp-server/.env",
          "jvm-mcp-server"
        ]
      }
    }
}

✨ Features

• Automatically download and manage the Arthas tool.
• Support local and remote Java process monitoring.
• Query the Java process list.
• Get real - time JVM thread information.
• Monitor JVM memory usage.
• Obtain thread stack trace information.
• Query class loading information.
• Support class and method decompilation.
• Monitor method calls.
• Dynamically adjust the log level.
• AI - driven JVM performance analysis.

📦 Installation

System Requirements

• Python 3.10+
• Java Runtime Environment (JRE) 8+
• Internet connection (for downloading Arthas)
• SSH access to the target server (if using remote mode)

Installation Steps

1. Install the uv tool

## Linux Shell
curl -LsSf https://astral.sh/uv/install.sh | sh
## Or install with pip
pip install uv
## Or use pipx (if pipx is installed)
pipx install uv 
## Windows PowerShell
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

2. Clone the project

git clone https://github.com/xzq-xu/jvm-mcp-server.git
cd jvm-mcp-server

3. Initialize the project environment using uv

# Create a virtual environment
uv venv
# Synchronize project dependencies
uv sync

4. Configure environment variables (optional, for remote connection)

Create a .env file and add the following configuration:

# Linux/Mac
ARTHAS_SSH_HOST=user@remote-host
ARTHAS_SSH_PORT=22  # Optional, default is 22
ARTHAS_SSH_PASSWORD=your-password  # If using password authentication

# Windows PowerShell
$env:ARTHAS_SSH_HOST="user@remote-host"
$env:ARTHAS_SSH_PORT="22"  # Optional, default is 22
$env:ARTHAS_SSH_PASSWORD="your-password"  # If using password authentication

⚠️ Important Note

Regarding the AI - driven JVM performance analysis, ensure that the relevant AI models and data are properly configured and maintained.