Spring Ai Example

🚀 Spring AI Sample Project

This project demonstrates various implementation patterns and best practices for using Spring AI tools. It consists of two main modules:

• mcp-server: Implements a Model Context Protocol (MCP) server supporting Server-Sent Events (SSE) for both WebFlux and WebMvc.
• proposal-agent: Implements an MCP client for generating AI-driven proposals.

📦 Project Structure

.
├── mcp-server/           # MCP server implementation
│   ├── src/             # Server source code
│   └── README.md        # Server documentation
├── proposal-agent/      # MCP client implementation
│   ├── src/             # Client source code
│   └── README.md        # Client documentation
└── src/                 # Common source code

✨ Tool Implementation Patterns

Method as a Tool

Spring AI supports defining methods as tools using the @Tool annotation. For example, the following method from DateTimeTools:

@Tool(name = "getCurrentDateTime", description = "Get the current date and time")
public String getCurrentDateTime() {
    return LocalDateTime.now().atZone(LocaleContextHolder.getTimeZone().toZoneId()).toString();
}

Tool Result Converter

You can implement a custom result converter to control the format of tool results. For example, the following method from CustomToolCallResultConverter:

@Tool(name = "getCustomer",
      description = "Retrieve customer information",
      resultConverter = CustomToolCallResultConverter.class)
public Customer getCustomer(String name, ToolContext context) {
    return new Customer(name, "example@email.com");
}

Tool Context

Spring AI provides a ToolContext parameter that can be injected into tool methods to access context information:

public Customer getCustomerByEmail(String email, ToolContext context) {
    log.info("Context: {}", context);
    return new Customer("Demo", email);
}

Tool Parameters

You can provide descriptions for tool parameters by using the @ToolParam annotation. For example, the following method:

@Tool(name = "setAlarm")
public void setAlarm(@ToolParam(description = "Date and time in ISO-8601 format") String time) {
    // Implementation
}

⚙️ Configuration

This project uses Spring Boot and is configured with the following key settings:

• Ollama AI model integration
• Vector storage (PGVector)
• H2 database for development
• CORS configuration to support web access
• MCP server implementation
• MCP client implementation
• SSE implementation for real-time updates

🔧 Technology Stack

• Spring Boot
• Spring AI
• Ollama AI model
• PGVector vector storage
• H2 database
• CORS configuration
• SSE (Server-Sent Events) for real-time updates