mcpField
S
Simple MCP Server

Simple MCP Server

Local
github.com/xiaobo187Media & Design1Updated 81w ago

About Simple MCP Server

Simple MCP Server is an example project for developers learning to build MCP servers, using weather lookup as its demonstration. It calls the Amap Open Platform API for current and forecast weather and shows how an AI client invokes the service.

Key features

  1. 01Query weather through the Amap API
  2. 02Retrieve current and forecast weather
  3. 03Use STDIO transport
  4. 04Provide a Maven build process

Use cases

  1. 01Learn to build a basic MCP server
  2. 02Ask for city weather in an AI conversation

MCP support

The MCP server exposes weather lookup to compatible clients over STDIO and returns results from the Amap API.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Simple MCP Server

这是一个示例项目,用极简方式演示如何构建MCP Server。

  • 天气查询:使用高德开放平台提供的天气查询API实现MCP Server,可获取实况和未来天气.

效果演示

Cherry Studio使用

如上图:

  • 用户问"西安今天用穿棉袄吗"
  • AI自动判断是否要调用天气MCP Server
  • AI按照MCP Server的参数要求,将西安的经纬度信息提供给MCP Server
  • MCP Server内部调用了高德提供的天气查询API,并将结果返回给AI
  • AI将天气结果进行汇总整理,输出给用户

环境准备

MCP Server 构建和执行
  • Java 17 or later
  • Maven 3.6 or later
  • Understanding of Spring Boot and Spring AI concepts
  • (Optional) Claude Desktop for AI assistant integration
MCP Client和大模型

支持MCP协议的任何AI对话客户端程序都可以,如:Cline、Continue、Claude Desktop等, 本例使用Cherry Studio。

Cherry Studio

Cherry Studio是一个AI对话客户端,其支持很多个大模型提供商,如:硅基流动、阿里云百炼、OpenAI等几十个国内外提供商,各提供商分别提供很多大模型服务,各个大模型的能力也有差异,有免费和收费的,也有不同作用和能力的。 当然,Cherry Studio也支持本地运行的大模型,如:Ollama、LLM Studio等。

本文使用硅基流动提供的Qwen2.5-7B-Instruct模型,请先注册硅基流动账户,申请API密钥,并在Cherry Studio中配置API密钥。

注意:请选择带有Function Call功能的大模型(Cherry Studio中带🔧符合的大模型),如:Qwen2.5-7B-Instruct。

配置大模型和密钥

高德开放平台API密钥

从高德开放平台申请Web API密钥(key)。

构建

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

构建完成后,在项目路径下会产生target/mcp-weather-stdio-server-0.0.1-SNAPSHOT.jar文件。

安装使用

在 Cherry Studio中打开设置/MCP服务器,添加MCP服务器,如下图:

添加MCP服务器

  • 名称: 随意写
  • 类型:STDIO
  • 命令:node
  • 参数:刚才构建的执行文件路径,即/Users/yourname/simple-mcp-server/build/index.js
  • 环境变量:
    • GAODE_API_KEY :高德开放平台申请的Web API 32位密钥 GAODE_API_KEY=your_api_key
    • DINGTALK_ACCESS_TOKEN: 创建钉钉群机器人的Webhook 地址后面的64位密钥 DINGTALK_ACCESS_TOKEN=your_access_token

使用

在Cherry Studio中新建对话,对话框下方开启MCP服务器和刚才安装的MCP Server。

注意:当选择了带有Function Call功能的大模型时,下方才有MCP相关选项。

使用MCP对话

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.