MCP Weather Stdio Server

🚀 Simple MCP Server

This is a sample project demonstrating how to build an MCP Server in a minimalist way.

• Weather Query: Implement the MCP Server using the Weather Query API provided by AutoNavi Open Platform to obtain real-time and future weather information.

✨ Features

As shown in the above figure:

• User Inquiry: "Do I need to wear a cotton-padded jacket in Xi'an today?"
• AI automatically determines whether to call the Weather MCP Server.
• AI provides the latitude and longitude information of Xi'an to the MCP Server according to its requirements.
• The MCP Server internally calls the weather query API provided by AutoNavi and returns the results to the AI.
• AI summarizes and organizes the weather information and outputs it to the user.

📦 Installation

Building and Running the MCP Server

• Java 17 or higher
• Maven 3.6 or higher
• Understanding of Spring Boot and Spring AI concepts
• (Optional) Use of AI assistant tools such as Claude Desktop

MCP Client and Large Models

Any AI dialogue client program supporting the MCP protocol can be used, such as Cline, Continue, Claude Desktop, etc. In this article, Cherry Studio is used.

Cherry Studio is an AI dialogue client that supports many large model providers at home and abroad, such as SiliconFlow, Alibaba Cloud Bailian, OpenAI, etc. Each provider has multiple large model services with different functions and performances, covering both free and paid options.

In this article, the Qwen2.5-7B-Instruct model provided by SiliconFlow is used. Please register a SiliconFlow account first, apply for an API key, and configure it in Cherry Studio.

⚠️ Important Note

Please choose a large model that supports the Function Call feature (large models marked with the 🔧 icon in Cherry Studio), such as Qwen2.5-7B-Instruct.

AutoNavi Open Platform API Key

Apply for a Web API key (key) from the AutoNavi Open Platform.

🚀 Quick Start

The MCP server uses the STDIO transmission mode and is usually started automatically by the client. To build the server jar:

./mvnw clean install -DskipTests

After the build is complete, the target/mcp-weather-stdio-server-0.0.1-SNAPSHOT.jar file will be generated in the project directory.

Installation and Usage

Open Settings > MCP Server in Cherry Studio and add an MCP server, as shown in the following figure:

• Name: Fill in at will.
• Type: STDIO
• Command: java
• MCP configuration parameters (copy and paste the Copy configuration parameters as shown in the screenshot):

{
    "servers": [
        {
            "id": "mcp-server-id",
            "name": "MCP Server Name",
            "description": "MCP Server Description",
            "type": "stdio",
            "command": "java -jar target/mcp-weather-stdio-server-0.0.1-SNAPSHOT.jar"
        }
    ]
}

Usage Instructions

Enable the MCP function in Cherry Studio and follow these steps:

⚠️ Important Note

• Choose a large model that supports Function Call.
• Ensure that all dependencies and configurations are correct.
• Run the server after the build is complete.