Addition MCP Server

Addition MCP Server

A simple demonstration MCP server that provides a basic arithmetic tool for adding two numbers together, showcasing how to build custom MCP servers with input validation.

Category
访问服务器

README

My MCP Server

A simple Model Context Protocol (MCP) server that provides an addition tool for adding two numbers together.

Overview

This MCP server implements a basic arithmetic tool that can add two numbers. It's built using the official MCP SDK and demonstrates how to create a custom MCP server.

Features

  • Addition Tool: Adds two numbers together
  • MCP Protocol: Follows the Model Context Protocol specification
  • Type Safety: Uses Zod for input validation

Installation

  1. Clone or download this repository
  2. Install dependencies:
    npm install
    

Usage

Running the Server

To run the MCP server:

node mcp.js

The server will start and listen for MCP protocol messages via stdio.

Available Tools

Addition Tool

  • Name: add
  • Description: Add two numbers together
  • Parameters:
    • a (number): First number
    • b (number): Second number
  • Returns: The sum of the two numbers as text

Example Usage

When connected to an MCP client, you can use the addition tool like this:

{
  "tool": "add",
  "parameters": {
    "a": 5,
    "b": 3
  }
}

This would return: 8

Adding to Cursor

To use this MCP server in Cursor, you need to configure it in your Cursor settings:

Method 1: Using Cursor Settings UI

  1. Open Cursor Settings:

    • Press Cmd+, (Mac) or Ctrl+, (Windows/Linux)
    • Or go to Cursor > Preferences > Settings
  2. Navigate to MCP Settings:

    • Search for "MCP" in the settings search bar
    • Click on "Model Context Protocol" settings
  3. Add the Server:

    • Click "Add Server" or the "+" button
    • Configure the server with these settings:
      Name: Addition Server
      Command: node
      Args: [path/to/your/mcp.js]
      Cwd: [path/to/your/project/directory]
      

Method 2: Using Settings JSON

  1. Open Cursor Settings JSON:

    • Press Cmd+Shift+P (Mac) or Ctrl+Shift+P (Windows/Linux)
    • Type "Preferences: Open Settings (JSON)"
    • Select it
  2. Add MCP Configuration: Add this configuration to your settings JSON:

    {
      "mcp.servers": {
        "addition-server": {
          "command": "node",
          "args": ["/Users/slav/Documents/dev/first-mcp/mcp.js"],
          "cwd": "/Users/slav/Documents/dev/first-mcp"
        }
      }
    }
    

    Important: Replace the paths with your actual project directory path.

  3. Restart Cursor:

    • Close and reopen Cursor for the changes to take effect

Using the Addition Tool in Cursor

Once configured, you can use the addition tool in Cursor by:

  1. Opening a chat with the AI assistant
  2. Asking it to add numbers: "Can you add 15 and 27 for me?"
  3. The AI will use your MCP server to perform the calculation

Troubleshooting

  • Server not found: Make sure the path to mcp.js is correct and the file exists
  • Permission errors: Ensure you have execute permissions on the Node.js binary
  • Dependencies missing: Run npm install in the project directory first
  • Port conflicts: This server uses stdio, so no port conflicts should occur

Development

Project Structure

  • mcp.js - Main server implementation
  • package.json - Node.js project configuration
  • README.md - This file

Dependencies

  • @modelcontextprotocol/sdk - Official MCP SDK
  • zod - Type validation library

License

ISC

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选