Server2MCP Spring Boot Starter

What is Server2MCP Spring Boot Starter?

Server2MCP Spring Boot Starter automatically scans existing Spring Boot @RestController and @Service beans and exposes them as MCP (Model Context Protocol) tools with minimal configuration. It combines parsers from Swagger/OpenAPI, Javadoc, Spring MVC metadata, Jackson, and Spring AI to turn REST APIs into AI-callable tools without rewriting business logic. It is designed for developers who want to add MCP support to existing Spring Boot projects with zero-to-low code changes.

How to use Server2MCP Spring Boot Starter?

Add the dependency (build from source — not yet on Maven Central), enable it in application.yml with plugin.mcp.enabled: true, configure parser order and scan scope, and optionally set up Javadoc parsing by packaging source files. Start your application; the MCP endpoint is ready at /mcp by default and can be tested with any MCP client like Cursor or Continue.

Key features of Server2MCP Spring Boot Starter

• Non-intrusive — no need to change existing business code
• Auto-discovery — scans controllers and services to register methods as MCP tools
• Multi-parser support — combines descriptions from Swagger, Javadoc, Spring MVC, and more
• Custom annotations — @ToolScan, @ResourceScan, @PromptScan for fine-grained control
• Isolated MCP tool system — uses its own McpTool annotation independent of Spring AI
• Full MCP SDK compatibility — supports callbacks, resources, and prompts

Use cases of Server2MCP Spring Boot Starter

• Expose internal management system APIs to AI agents quickly
• Build multi-agent systems by turning microservices into MCP tools
• Prototype AI features on top of production REST services
• Avoid duplicating logic between REST and MCP endpoints

FAQ from Server2MCP Spring Boot Starter

How does this differ from manually adding @Tool annotations?

It automatically scans existing REST controllers, requiring only configuration changes instead of annotating every method. The comparison table shows minimal code changes compared to medium-to-high for alternatives.

What are the runtime requirements?

Java 17 or later and Spring Boot 3.x.

Is the project available on Maven Central?

Not yet — you must build from source by cloning the repository and running mvn clean install.

How do I enable Javadoc parsing in production?

Package source files using the maven-resources-plugin to copy .java files into the build output directory, since bytecode does not contain Javadoc comments.

What is the default MCP endpoint?

The MCP endpoint is available at /mcp by default and can be configured via spring.ai.mcp.* properties.