JVM Diagnostics MCP Server

@brunoborges

Repository

Basic information

About JVM Diagnostics MCP Server

MCP Server for starting new projects

#java #jvm #diagnostics #mcp #server

JVM Diagnostics MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "jvm-diagnostics": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "JAVA_HOME",
        "ghcr.io/brunoborges/jvm-diagnostics-mcp:latest"
      ],
      "env": {
        "JAVA_HOME": "/path/to/java/home"
      }
    }
  }
}

JVM Diagnostics MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is JVM Diagnostics MCP?

JVM Diagnostics MCP is an MCP server that wraps various JVM diagnostic command-line tools (jstat, jcmd, jps) and exposes them through a prompt-enhanced interface. It is intended for developers and operations personnel who need to monitor and diagnose JVM processes locally.

How to use JVM Diagnostics MCP?

Install by downloading the JAR from the GitHub release page and configuring the server in Claude Desktop or VS Code Insiders, or run it inside a Docker container. The server operates via stdio transport and requires Java 17+ (or Docker) with JVM diagnostic tools available in the environment.

Key features of JVM Diagnostics MCP

Wraps jstat, jcmd, and jps diagnostic tools
Adds a prompt to improve tool interaction with LLMs
Monitors JVM performance metrics
Inspects and manages JVM processes
Analyzes thread dumps, heap dumps, and other diagnostics

Use cases of JVM Diagnostics MCP

Monitoring live JVM performance metrics using jstat
Listing and inspecting running Java processes with jps
Executing diagnostic commands on a JVM via jcmd
Capturing and analyzing thread dumps and heap dumps

Frequently asked questions

What does JVM Diagnostics MCP do?

It wraps JVM command-line diagnostics tools (jstat, jcmd, jps) and exposes them as MCP tools with an enhanced prompt, enabling an LLM to run JVM diagnostics interactively.

Is it safe to use?

The README advises caution because the server is LLM-driven; users should validate generated commands. The software is provided “as is” without warranty, and you use it at your own risk.

Is it secured and should I run it on a remote server?

No. The server uses only the stdio transport and is intended to run locally on your machine. It is not secured and could be exploited if accessible remotely.

How do I install JVM Diagnostics MCP?

You can run it as a Java application (requires Java 17+) by downloading the JAR from the GitHub release page, or run it inside a Docker container. Configuration examples for Claude Desktop and VS Code Insiders are provided in the README.

What are the runtime dependencies?

Java 17 or higher is required, and JVM diagnostic tools (jstat, jcmd, jps) must be available in the environment. Docker is an alternative runtime if Java is not installed locally.

Comments

More Developer Tools MCP servers

Cronwatch

cronwatchdev

CronWatch records every run of your scheduled jobs in your own database, and speaks up when one is missed, fails, gets stuck, runs slow or costs too much. CronWatch is free and open-source.

Total CMS

Joe Workman

Read-only Total CMS docs and site content over MCP: exact Twig signatures, field types, schema options, the CLI, release notes and comparisons. No key required.

OrangePro

Aamir Siddiqui

OrangePro local-first CLI + MCP server for behavior mapping, grounded test generation, and dynamic proof.

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci