convez.ai
MCP ServerDevOps & InfraestruturaAvançado
xzq-xu

JVM MCP Server

xzq-xu/jvm-mcp-server

Monitoramento JVM leve com zero dependências via protocolo MCP

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP baseado em ferramentas nativas do JDK para monitoramento e diagnóstico de aplicações Java. Oferece aos agentes de IA capacidades avançadas de análise sem dependências externas, suportando monitoramento local e remoto via SSH.

Instalação

$npx convez-ai xzq-xu/jvm-mcp-server

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
91
Forks
19
Acompanhando
5
Saúde
42%
Último commit
há 7 meses
Versão
—
Issues abertas
3
Contribuidores
8

Casos de uso

  • Monitoramento em tempo real de aplicações Java
  • Análise de stack traces e threads de JVMs remotas
  • Diagnóstico de problemas de performance e memória
  • Inspeção de classes e decompilação de bytecode
  • Integração de agentes IA com ecosistema Java

Veredito

Solução técnica sólida para integração de IA com infraestrutura Java, com design minimalista usando apenas ferramentas nativas do JDK. Ideal para equipes que precisam de monitoramento JVM programável sem overhead adicional.

README

A tradução para o português deste README ainda está na fila.

JVM MCP Server

English | 中文

MseeP.ai Security Assessment Badge

A lightweight JVM monitoring and diagnostic MCP (Multi-Agent Communication Protocol) server implementation based on native JDK tools. Provides AI agents with powerful capabilities to monitor and analyze Java applications without requiring third-party tools like Arthas.

Hosted deployment

A hosted deployment is available on Fronteir AI.

Features

  • Zero Dependencies: Uses only native JDK tools (jps, jstack, jmap, etc.)
  • Lightweight: Minimal resource consumption compared to agent-based solutions
  • High Compatibility: Works with all Java versions and platforms
  • Non-Intrusive: No modifications to target applications required
  • Secure: Uses only JDK certified tools and commands
  • Remote Monitoring: Support for both local and remote JVM monitoring via SSH

Core Capabilities

Basic Monitoring

  • Java process listing and identification
  • JVM basic information retrieval
  • Memory usage monitoring
  • Thread information and stack trace analysis
  • Class loading statistics
  • Detailed class structure information

Advanced Features

  • Method call path analysis
  • Class decompilation
  • Method search and inspection
  • Method invocation monitoring
  • Logger level management
  • System resource dashboard

System Requirements

  • Python 3.6+
  • JDK 8+
  • Linux/Unix/Windows OS
  • SSH access (for remote monitoring)

Installation

Using uv (Recommended)

# Install uv if not already installed
curl -LsSf https://astral.sh/uv/install.sh | sh  # Linux/macOS
# or
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"  # Windows

# Install the package
uv pip install jvm-mcp-server

Using pip

pip install jvm-mcp-server

From Source

# Clone the repository
git clone https://github.com/your-repo/jvm-mcp-server.git
cd jvm-mcp-server

# Using uv (recommended)
uv venv  # Create virtual environment
uv sync  # Install dependencies

# Or install in development mode
uv pip install -e .

Quick Start

Starting the Server

Using uv (Recommended)

# Local mode
uv run jvm-mcp-server

# Using environment variables file for remote mode
uv run --env-file .env jvm-mcp-server

# In specific directory
uv --directory /path/to/project run --env-file .env jvm-mcp-server

Using uvx

# Local mode
uvx run jvm-mcp-server

# With environment variables
uvx run --env-file .env jvm-mcp-server

Using Python directly

from jvm_mcp_server import JvmMcpServer

# Local mode
server = JvmMcpServer()
server.run()

# Remote mode (via environment variables)
# Set SSH_HOST, SSH_PORT, SSH_USER, SSH_PASSWORD or SSH_KEY
import os
os.environ['SSH_HOST'] = 'user@remote-host'
os.environ['SSH_PORT'] = '22'
server = JvmMcpServer()
server.run()

Using with MCP Configuration

{
  "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"
      ]
    }
  }
}

Available Tools

JVM-MCP-Server provides a comprehensive set of tools for JVM monitoring and diagnostics:

  • list_java_processes: List all Java processes
  • get_thread_info: Get thread information for a specific process
  • get_jvm_info: Get JVM basic information
  • get_memory_info: Get memory usage information
  • get_stack_trace: Get thread stack trace information
  • get_class_info: Get detailed class information including structure
  • get_stack_trace_by_method: Get method call path
  • decompile_class: Decompile class source code
  • search_method: Search for methods in classes
  • watch_method: Monitor method invocations
  • get_logger_info: Get logger information
  • set_logger_level: Set logger levels
  • get_dashboard: Get system resource dashboard
  • get_jcmd_output: Execute JDK jcmd commands
  • get_jstat_output: Execute JDK jstat commands

For detailed documentation on each tool, see Available Tools.

Architecture

JVM-MCP-Server is built on a modular architecture:

  1. Command Layer: Wraps JDK native commands
  2. Executor Layer: Handles local and remote command execution
  3. Formatter Layer: Processes and formats command output
  4. MCP Interface: Exposes functionality through FastMCP protocol

Key Components

  • BaseCommand: Abstract base class for all commands
  • CommandExecutor: Interface for command execution (local and remote)
  • OutputFormatter: Interface for formatting command output
  • JvmMcpServer: Main server class that registers all tools

Development Status

The project is in active development. See Native_TODO.md for current progress.

Completed

  • Core architecture and command framework
  • Basic commands implementation (jps, jstack, jmap, jinfo, jcmd, jstat)
  • Class information retrieval system
  • MCP tool parameter type compatibility fixes

In Progress

  • Caching mechanism
  • Method tracing
  • Performance monitoring
  • Error handling improvements

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Fork the repository
  2. Create your feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

NP|## Acknowledgements #MH| #TK|- JDK tools documentation #WY|- FastMCP protocol specification #JK|- Contributors and testers #BP| #KG|## Permission Requirements #YM| #KB|Some JVM diagnostic commands (jstack, jmap, jinfo, jcmd, etc.) require sufficient permissions to attach to the target JVM process. If you encounter permission errors, try the following solutions: #YB| #KB|### Common Errors #RR| #KB|- Permission denied: Insufficient permissions #YZ|- Unable to open socket file: Cannot connect to JVM process #KD|- No such process: Process does not exist or has exited #MH| #KB|### Solutions #BR| #KB|1. Run with sudo (recommended): sudo uv run jvm-mcp-server #XZ|2. Run as the same user as target Java process: Check the user ID of the Java process and run as that user #HM|3. Add experimental attach permission to JDK: Add to JVM startup arguments:

```

-XX:+AllowRedefinitionToAddDeleteMethods

```

#XQ|4. In Docker: Ensure the container has sufficient permissions (--privileged or mount /proc) #KB| #KB|Note: list_java_processes uses the jps command and does not require special permissions. Other commands may need to be configured according to the solutions above.

  • JDK tools documentation
  • FastMCP protocol specification
  • Contributors and testers
Ver o original no GitHub

Bom para

Relacionados