Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Spring AI MCP Weather STDIO Server - A Spring Boot starter project demonstrating how to build a Model Context Protocol (MCP) server that provides weather-related tools

NotificationsYou must be signed in to change notification settings

cloud4java/my-mcp-stdio-server

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

A Spring Boot starter project demonstrating how to build a Model Context Protocol (MCP) server that provides weather-related tools using the National Weather Service (weather.gov) API. This project showcases the Spring AI MCP Server Boot Starter capabilities with STDIO transport implementation.

For more information, see theMCP Server Boot Starter reference documentation.

Prerequisites

  • Java 17 or later
  • Maven 3.6 or later
  • Understanding of Spring Boot and Spring AI concepts
  • (Optional) Claude Desktop for AI assistant integration

About Spring AI MCP Server Boot Starter

Thespring-ai-mcp-server-spring-boot-starter provides:

  • Automatic configuration of MCP server components
  • Support for both synchronous and asynchronous operation modes
  • STDIO transport layer implementation
  • Flexible tool registration through Spring beans
  • Change notification capabilities

Project Structure

About Spring AI MCP Server Boot Starter

Thespring-ai-mcp-server-spring-boot-starter provides:

  • Automatic configuration of MCP server components
  • Support for both synchronous and asynchronous operation modes
  • STDIO transport layer implementation
  • Flexible tool registration through Spring beans
  • Change notification capabilities

Project Structure

src/├── main/│   ├── java/│   │   └── org/springframework/ai/mcp/sample/server/│   │       ├── McpServerApplication.java    # Main application class with tool registration│   │       └── WeatherService.java          # Weather service implementation with MCP tools│   └── resources/│       └── application.properties           # Server and transport configuration└── test/    └── java/        └── org/springframework/ai/mcp/sample/client/            └── ClientStdio.java             # Test client implementation

Building and Running

The server uses STDIO transport mode and is typically started automatically by the client. To build the server jar:

./mvnw clean install -DskipTests

Tool Implementation

The project demonstrates how to implement and register MCP tools using Spring's dependency injection and auto-configuration:

@ServicepublicclassWeatherService {@Tool(description ="Get weather forecast for a specific latitude/longitude")publicStringgetWeatherForecastBrazil(doublelatitude,// Latitude coordinatedoublelongitude// Longitude coordinate    ) {// Implementation    }@Tool(description ="Get weather alerts for a US state")publicStringgetAlerts(Stringstate// Two-letter US state code (e.g., CA, NY)    ) {// Implementation    }}@SpringBootApplicationpublicclassMcpServerApplication {@BeanpublicList<ToolCallback>weatherTools(WeatherServiceweatherService) {returnToolCallbacks.from(weatherService);    }}

The auto-configuration automatically registers these tools with the MCP server. You can have multiple beans producing lists of ToolCallbacks, and the auto-configuration will merge them.

Available Tools

1. Weather Forecast Tool

@Tool(description ="Get weather forecast for a specific latitude/longitude")publicStringgetWeatherForecastBrazil(doublelatitude,// Latitude coordinatedoublelongitude// Longitude coordinate) {// Returns detailed forecast including:// - Temperature and unit// - Wind speed and direction// - Detailed forecast description}// Example usage:CallToolResultforecast =client.callTool(newCallToolRequest("getWeatherForecastBrazil",Map.of("latitude",47.6062,// Seattle coordinates"longitude", -122.3321        )    ));

2. Weather Alerts Tool

@Tool(description ="Get weather alerts for a US state")publicStringgetAlerts(Stringstate// Two-letter US state code (e.g., CA, NY)) {// Returns active alerts including:// - Event type// - Affected area// - Severity// - Description// - Safety instructions}// Example usage:CallToolResultalerts =client.callTool(newCallToolRequest("getAlerts",Map.of("state","NY")    ));

Client Integration

Java Client Example

Create MCP Client Manually

// Create server parametersServerParametersstdioParams =ServerParameters.builder("java")    .args("-Dspring.ai.mcp.server.transport=STDIO","-Dspring.main.web-application-type=none","-Dlogging.pattern.console=","-jar","target/my-mcp-stdio-server-0.0.1-SNAPSHOT.jar")    .build();// Initialize transport and clientvartransport =newStdioClientTransport(stdioParams);varclient =McpClient.sync(transport).build();

TheClientStdio.java demonstrates how to implement an MCP client manually.

For a better development experience, consider using theMCP Client Boot Starters. These starters enable auto-configuration of multiple STDIO and/or SSE connections to MCP servers. See thestarter-default-client andstarter-webflux-client projects for examples.

Use MCP Client Boot Starter

Use thestarter-default-client to connect to the weatherstarter-stdio-server:

  1. Follow thestarter-default-client readme instructions to build amcp-starter-default-client-0.0.1-SNAPSHOT.jar client application.

  2. Run the client using the configuration file:

java -Dspring.ai.mcp.client.stdio.connections.server1.command=java \     -Dspring.ai.mcp.client.stdio.connections.server1.args=-jar,/Users/christiantzolov/Dev/projects/spring-ai-examples/model-context-protocol/weather/starter-stdio-server/target/my-mcp-stdio-server-0.0.1-SNAPSHOT.jar \     -Dai.user.input='What is the weather in NY?' \     -Dlogging.pattern.console= \     -jar mcp-starter-default-client-0.0.1-SNAPSHOT.jar

Claude Desktop Integration

To integrate with Claude Desktop, add the following configuration to your Claude Desktop settings:

{"mcpServers": {"spring-ai-mcp-weather": {"command":"java","args": ["-Dspring.ai.mcp.server.stdio=true","-Dspring.main.web-application-type=none","-Dlogging.pattern.console=","-jar","/absolute/path/to/my-mcp-stdio-server-0.0.1-SNAPSHOT.jar"      ]    }  }}

Replace/absolute/path/to/ with the actual path to your built jar file.

Configuration

Application Properties

All properties are prefixed withspring.ai.mcp.server:

# Required STDIO Configurationspring.main.web-application-type=nonespring.main.banner-mode=offlogging.pattern.console=# Server Configurationspring.ai.mcp.server.enabled=truespring.ai.mcp.server.name=my-weather-serverspring.ai.mcp.server.version=0.0.1# SYNC or ASYNCspring.ai.mcp.server.type=SYNCspring.ai.mcp.server.resource-change-notification=truespring.ai.mcp.server.tool-change-notification=truespring.ai.mcp.server.prompt-change-notification=true# Optional file logginglogging.file.name=my-mcp-stdio-server.log

Key Configuration Notes

  1. STDIO Mode Requirements

    • Disable web application type (spring.main.web-application-type=none)
    • Disable Spring banner (spring.main.banner-mode=off)
    • Clear console logging pattern (logging.pattern.console=)

  2. Server Type

    • SYNC (default): UsesMcpSyncServer for straightforward request-response patterns
    • ASYNC: UsesMcpAsyncServer for non-blocking operations with Project Reactor support

Additional Resources

About

Spring AI MCP Weather STDIO Server - A Spring Boot starter project demonstrating how to build a Model Context Protocol (MCP) server that provides weather-related tools

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

[8]ページ先頭
©2009-2025 Movatter.jp