jvm-mcp-server

This is an implementation project of a JVM-based MCP (Model Context Protocol) server. The project aims to provide a standardized MCP server implementation for the JVM platform, enabling AI models to better interact with the Java ecosystem.

by xzq-xu
59 stars
10 forks
Available MCP Tools 0 tools

Model Context Protocol tools provided by this server

No tools information available for this server.

Check the GitHub repository or documentation for more details.

README

English | 中文

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

Features

  • Automatic download and management of Arthas tools
  • Support for local and remote Java process monitoring
  • Java process list querying
  • Real-time JVM thread information
  • JVM memory usage monitoring
  • Thread stack trace information
  • Class loading information querying
  • Support for class and method decompilation
  • Method call monitoring
  • Dynamic log level adjustment
  • AI-driven JVM performance analysis

System Requirements

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

Installation and Environment Setup

1. Install uv tool

## linux shell
curl -LsSf https://astral.sh/uv/install.sh | sh
## or install using pip
pip install uv
## or install using pipx (if you have pipx 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 project environment using uv

uv venv
uv sync

4. Configure environment variables (Optional, for remote connections)

Create a .env file and add the following configurations:

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

$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

Quick Start

  1. Start the server using uv:
uv run jvm-mcp-server

uv run --env-file .env jvm-mcp-server

uv --directory /path/to/project run --env-file .env jvm-mcp-server
  1. Use in Python code:
from jvm_mcp_server import JvmMcpServer

server = JvmMcpServer()
server.run()
  1. Using MCP tools:

Using 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"
        ]
      }
    }
}

Without using configuration file, it will read system environment variables, if not present it will monitor local threads:

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

Available Tools

Available Tools List

Important Notes

  1. Ensure Java is installed in the runtime environment
  2. Arthas tool will be automatically downloaded on first run (arthas will be downloaded to home directory, can be downloaded in advance and named as arthas-boot.jar)
  3. Requires access permissions to target Java process
  4. Remote mode requires SSH access and appropriate user permissions
  5. Recommended for use in development environment, production use should be carefully evaluated

Feedback

If you encounter any issues, please submit an Issue or Pull Request.

License

MIT License

Details
Category Developer Tools
Scope local
Language Python
License MIT License
OS Support
linux macos windows