Model Context Protocol Servers in Quarkus/Java
LocalAbout Model Context Protocol Servers in Quarkus/Java
This is a collection of MCP servers written in Java with the Quarkus MCP framework, maintained under Quarkiverse. Each server can be launched directly with jbang, covering databases, JVM inspection, file systems, containers and Kubernetes. It suits Java developers who want to extend LLM applications.
Key features
- 01Built on the Quarkus MCP server framework
- 02Runs directly with jbang without a manual build
- 03Provides a JDBC server for any JDBC database
- 04Provides a jvminsight server for running JVM processes
- 05Offers kubernetes and containers servers for infrastructure
Use cases
- 01Letting an LLM read and write a database through JDBC
- 02Inspecting a running JVM process
- 03Letting an LLM work with a Kubernetes cluster or containers
MCP support
Each server runs as an MCP server that exposes database, file system, container and other tools to MCP-enabled LLM applications such as Claude Desktop.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEModel Context Protocol Servers in Quarkus/Java
This project contains Model Context Protocol servers, implemented in Java using the Quarkus MCP server framework.
These lets you extend the capabilities of your MCP enabled LLM (Large Language Model) AI applications.
These also work in MCP enabled LLM applications, like Claude Desktop. You can find other clients on Awesome MCP Clients page.
Running the servers
All of these servers are available to run with jbang everywhere: Java, JavaScript, Python and more. Where it says jbang it can be replaced with npx @jbangdev/jbang or uvx jbang or pipx jbang dependent on your preference.
Servers
jdbc

The jdbc server can be used to store and retrieve data from a database given just a JDBC URL. You can use any JDBC database, like Postgres, MySQL, Oracle, Sqlite, etc.
jbang jdbc@quarkiverse/quarkus-mcp-servers
See more in the jdbc readme.
jvminsight

The jvminsight server is a server that can be used to inspect a running JVM process.
jbang jvminsight@quarkiverse/quarkus-mcp-servers
See more in the jvminsight readme.
filesystem
The filesystem server is a file system server that can be used to serve files from a file system.
jbang filesystem@quarkiverse/quarkus-mcp-servers [path1] [path2] ...
See more in the filesystem readme.
jfx
The jfx server exposes a canvas that can be used to make drawings using JavaFX.
jbang jfx@quarkiverse/quarkus-mcp-servers
See more in the jfx readme.
kubernetes
The kubernetes server can be used to interact with a Kubernetes cluster.
jbang kubernetes@quarkiverse/quarkus-mcp-servers
containers
The 'containers' server lets you work with Docker/Podman/OCI compatible container engines.
jbang containers@quarkiverse/quarkus-mcp-servers

wolfram
The wolfram server can be used to perform web search optimized for use by a large language model through the Wolfram Alpha LLM API.
jbang wolfram@quarkiverse/quarkus-mcp-servers
Other Quarkus MCP based servers
WildFly
A WildFly MCP server that allows you to interact with WildFly running servers.
You can check this WildFly vlog that demonstrates its capabilities.
Read more in the WildFly MCP Server readme.
Ideas for other servers
If you have ideas for other servers, feel free to contribute them to this project.
If missing ideas, then look at the reference servers at https://github.com/modelcontextprotocol/servers and see if you can implement them in this project.
Other ideas:
- zulip
- jfr/java hooked to jmx/jfr
- quarkus dev mode
- ...
Contributing
If you have ideas for other servers, feel free to contribute them to this project.
To get started, clone the repository and build it:
git clone https://github.com/quarkiverse/quarkus-mcp-servers
cd quarkus-mcp-servers
mvn clean install
Then run the following command to generate a new server for i.e. jfr:
mkdir jfr
cd jfr
jbang init -t mcp jfr
This will create the jfr directory with a Hello World MCP server.
You can then build it:
mvn clean install
To wire it into the full project you need to add <module>jfr</module> to the root pom.xml file.
Make sure you have added some useful content to the README.md file + updated the demo image.
Then open a PR :)
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.
