Calculator MCP Server
Provides basic arithmetic operations (add, multiply, divide) for AI assistants through the Model Context Protocol.
README
Calculator MCP Server
A Model Context Protocol (MCP) server that provides mathematical calculation tools for AI assistants.
Features
This MCP server provides three core mathematical operations:
- Add - Add two numbers together with calculation history tracking
- Multiply - Multiply two numbers with optimized performance
- Divide - Divide numbers with comprehensive zero-division protection
The server maintains a calculation history and provides robust error handling for all mathematical operations.
Prerequisites
- Node.js (version 14 or higher)
- npm or yarn package manager
Installation
-
Clone or download this repository
-
Navigate to the project directory:
cd my-first-mcp-server -
Install dependencies:
npm install -
Build the TypeScript code:
npm run build
Running the Server
Development Mode
For development and testing:
npm run dev
Production Mode
For production use:
npm run start
Testing the Server
You can test if the server is working by sending an MCP request:
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | node dist/server.js
This should return a JSON response listing the available tools.
Integration with AI Clients
Cursor IDE
-
Create a
.cursor/mcp.jsonfile in your project root:{ "mcpServers": { "calculator": { "command": "node", "args": [ "/absolute/path/to/my-first-mcp-server/dist/server.js" ], "env": {} } } } -
Replace
/absolute/path/to/my-first-mcp-server/with the actual path to this directory -
Restart Cursor IDE
-
The calculator tools will be available to the AI assistant
Claude Desktop
-
Create or edit
~/Library/Application Support/Claude/claude_desktop_config.json:{ "mcpServers": { "calculator": { "command": "node", "args": ["/absolute/path/to/my-first-mcp-server/dist/server.js"] } } } -
Replace the path with your actual directory path
-
Restart Claude Desktop
Development
To modify or extend the calculator functionality:
- Edit the source files in the
src/directory - Rebuild the project:
npm run build - Test your changes:
npm run dev
Configuration
The server can be configured using environment variables. Copy .env.example to .env and modify as needed.
Available configuration options:
NODE_ENV: Environment mode (development/production)PORT: Server port (default: 3000)LOG_LEVEL: Logging verbosityDB_*: Database connection settings
Docker Support
You can run the entire stack using Docker Compose:
docker-compose up -d
This will start:
- Calculator MCP Server
- PostgreSQL database (for calculation history)
- Redis cache
- Database administration interface
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests for new functionality
- Submit a pull request
License
This project is licensed under the ISC License.
Available Tools
add
Adds two numbers together.
Parameters:
a(number): First numberb(number): Second number
Example: add(25, 17) returns 42
multiply
Multiplies two numbers.
Parameters:
a(number): First numberb(number): Second number
Example: multiply(6, 7) returns 42
divide
Divides the first number by the second number.
Parameters:
a(number): Dividend (number to divide)b(number): Divisor (divide by this)
Example: divide(84, 2) returns 42
Note: Division by zero will return an error.
Using in Other Projects
Option 1: Absolute Path Reference
In any project where you want to use this calculator:
- Create
.cursor/mcp.jsonin that project's root - Reference the absolute path to this server's
dist/server.js - Restart your IDE
Option 2: Copy to Project
# Copy the entire MCP server to your project
cp -r /path/to/my-first-mcp-server /path/to/your-project/mcp-servers/calculator
# Update .cursor/mcp.json to use relative path:
{
"mcpServers": {
"calculator": {
"command": "node",
"args": ["./mcp-servers/calculator/dist/server.js"],
"env": {}
}
}
}
Option 3: NPM Package (Advanced)
You can publish this as an npm package for easier distribution:
- Update
package.jsonwith your package details - Run
npm publish - In other projects:
npm install your-calculator-mcp - Use
npx your-calculator-mcpin MCP configuration
Development
Scripts
npm run build- Compile TypeScript to JavaScriptnpm run dev- Run in development mode with tsxnpm run start- Run the compiled server
File Structure
my-first-mcp-server/
├── src/
│ └── server.ts # Main server implementation
├── dist/
│ └── server.js # Compiled JavaScript (generated)
├── .cursor/
│ └── mcp.json # Local MCP configuration
├── package.json # Node.js dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── README.md # This file
Troubleshooting
Server Not Connecting
- Ensure the path in
.cursor/mcp.jsonis correct and absolute - Verify the server builds successfully:
npm run build - Test the server manually:
echo '{"jsonrpc": "2.0", "id": 1, "method": "tools/list"}' | node dist/server.js - Restart your IDE after configuration changes
Tools Not Available
- Check that
.cursor/mcp.jsonis in the root of your working project - Ensure you're opening the correct project in your IDE
- Wait a few seconds after opening for MCP to initialize
- Check IDE developer console for MCP-related errors
Permission Issues
# Make sure the server file is executable
chmod +x dist/server.js
Server Details
- Protocol: Model Context Protocol (MCP)
- Transport: Standard I/O (stdio)
- Language: TypeScript/Node.js
- Framework: @modelcontextprotocol/sdk
License
ISC
Contributing
Feel free to extend this server with additional mathematical operations or features!
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。