This repository provides a Quarkus extension for implementing Model Context Protocol (MCP) servers, enabling seamless integration between LLM applications and external data sources through declarative and programmatic APIs.
This Quarkus extension facilitates the implementation of Model Context Protocol (MCP) servers, enabling seamless integration between LLM applications and external data sources/tools. MCP is an open protocol designed for AI-powered applications.
The extension offers declarative and programmatic APIs for easy implementation of MCP server features. LangChain4j provides the MCP client functionality.
To get started, add the quarkus-mcp-server-sse dependency to your project's POM file (or quarkus-mcp-server-stdio for STDIO transport). Define server features like prompts, resources, and tools using annotated business methods within CDI beans. The @Tool annotation defines tools, @Prompt defines prompts with arguments, and @Resource defines resources. Run your Quarkus application to start the MCP server.
Full documentation is available at https://quarkiverse.github.io/quarkiverse-docs/quarkus-mcp-server/dev/index.html.
Thanks to all contributors! This project follows the all-contributors specification.
quarkiverse/quarkus-mcp-server
December 11, 2024
March 28, 2025
Java