Jolokia
Let LLMs manage your Java application via JMX/Jolokia 🌶️
What is Jolokia?
Jolokia is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to let llms manage your java application via jmx/jolokia 🌶️
Let LLMs manage your Java application via JMX/Jolokia 🌶️
This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Let LLMs manage your Java application via JMX/Jolokia 🌶️
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx jolokiaConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use Jolokia
The Jolokia MCP server enables AI assistants and LLMs to manage and monitor Java applications via JMX (Java Management Extensions) through the Jolokia HTTP-to-JMX bridge. It exposes six tools covering MBean discovery, attribute reading/writing, and operation invocation — giving an AI agent the ability to inspect thread pools, tune heap settings, trigger garbage collection, deploy applications, and call any JMX-exposed management operation on a running Java process. This makes it ideal for AI-assisted operations, performance tuning, and incident investigation on JVM-based services.
Prerequisites
- Java 17+ JDK installed to run the Jolokia MCP server
- A running Java application instrumented with the Jolokia agent (jolokia.war or javaagent JAR) exposing a Jolokia HTTP endpoint (default: http://localhost:8778/jolokia)
- Download the jolokia-mcp runner JAR from the Jolokia GitHub releases page
- An MCP client such as Claude Desktop or Cursor
- Network access from the MCP server to the target application's Jolokia endpoint
Instrument your Java application with Jolokia
Attach the Jolokia JVM agent to your Java application so it exposes a Jolokia HTTP endpoint. This is the endpoint the MCP server will connect to.
# Start your Java app with the Jolokia javaagent
java -javaagent:jolokia-agent-jvm-2.x.x-javaagent.jar -jar your-app.jar
# Verify the endpoint is accessible:
curl http://localhost:8778/jolokia/versionDownload the Jolokia MCP runner JAR
Download the latest jolokia-mcp runner JAR from the Jolokia GitHub releases page at https://github.com/jolokia/jolokia-mcp-server/releases.
# Example download (check releases page for latest version)
curl -LO https://github.com/jolokia/jolokia-mcp-server/releases/download/v0.5.1/jolokia-mcp-0.5.1-runner.jarConfigure your MCP client
Add the Jolokia MCP server to your MCP client config. Point the runner JAR at your application's Jolokia endpoint by passing the URL as a positional argument.
{
"mcpServers": {
"jolokia": {
"command": "java",
"args": [
"-jar",
"/path/to/jolokia-mcp-0.5.1-runner.jar",
"http://localhost:8778/jolokia"
]
}
}
}Verify MBean discovery
Restart your MCP client and ask your AI assistant to list available MBeans. The listMBeans tool should return all JMX MBean names registered in the target JVM.
Explore and manage the application
Use the AI assistant to read attributes (e.g., heap memory usage), write attributes (e.g., log level), or invoke operations (e.g., garbage collection trigger) by referencing MBean names the AI discovered.
Jolokia Examples
Client configuration
Claude Desktop configuration for the Jolokia MCP server connecting to a local Java application's Jolokia endpoint.
{
"mcpServers": {
"jolokia": {
"command": "java",
"args": [
"-jar",
"/opt/jolokia/jolokia-mcp-0.5.1-runner.jar",
"http://localhost:8778/jolokia"
]
}
}
}Prompts to try
Example prompts for managing a Java application via Jolokia MBeans.
- "List all available MBeans in my Java application and group them by domain."
- "Read the HeapMemoryUsage attribute from the java.lang:type=Memory MBean and tell me what percentage of heap is in use."
- "List all operations available on the Catalina:type=Manager,context=/myapp,host=localhost MBean."
- "Invoke a garbage collection by calling the gc operation on java.lang:type=Memory."
- "Change the log level of the com.example package to DEBUG by writing to the appropriate Log4j MBean attribute."Troubleshooting Jolokia
Connection refused when connecting to the Jolokia endpoint
Verify the Java application is running and the Jolokia agent was attached correctly by curling http://localhost:8778/jolokia/version. If using a different port, update the Jolokia URL in the MCP config args accordingly. Check firewall rules if connecting to a remote host.
java -jar command fails with JAR not found error
Ensure the path to the jolokia-mcp runner JAR in the 'args' array is an absolute path and that the file exists at that location. Download the JAR from the Jolokia GitHub releases page and update the path in your config.
listMBeans returns an empty list or authentication error
If the Jolokia endpoint requires authentication, configure the Java agent with jolokia.user and jolokia.password system properties and pass credentials in the Jolokia URL (e.g., http://user:password@localhost:8778/jolokia). Check the Jolokia agent docs for authentication configuration options.
Frequently Asked Questions about Jolokia
What is Jolokia?
Jolokia is a Model Context Protocol (MCP) server that let llms manage your java application via jmx/jolokia 🌶️ It connects AI assistants to external tools and data sources through a standardized interface.
How do I install Jolokia?
Follow the installation instructions on the Jolokia GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with Jolokia?
Jolokia works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is Jolokia free to use?
Yes, Jolokia is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.
Jolokia Alternatives — Similar Monitoring & Observability Servers
Looking for alternatives to Jolokia? Here are other popular monitoring & observability servers you can use with Claude, Cursor, and VS Code.
Netdata
★ 78.9kReal-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Kubeshark
★ 11.9keBPF-powered network observability for Kubernetes. Indexes L4/L7 traffic with full K8s context, decrypts TLS without keys. Queryable by AI agents via MCP and humans via dashboard.
Mission Control
★ 4.9kSelf-hosted AI agent orchestration platform: dispatch tasks, run multi-agent workflows, monitor spend, and govern operations from one mission control dashboard.
Grafana
★ 3.0kThis MCP server enables natural-language querying of Grafana logs by automatically detecting log sources and service labels. It provides read-only access to log data with intelligent caching for efficient repeat queries.
Sentrux
★ 2.4kReal-time architectural sensor that helps AI agents close the feedback loop, enabling recursive self-improvement of code quality. Pure Rust.
OpenInference
★ 986OpenTelemetry Instrumentation for AI Observability
Browse More Monitoring & Observability MCP Servers
Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up Jolokia 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 Jolokia?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.