MCP Math Server
Provides basic mathematical operations including arithmetic, square root, and number theory functions like GCD and LCM. Built with TypeScript and includes proper error handling for edge cases like division by zero.
README
MCP Math Server
A Model Context Protocol (MCP) server built with TypeScript and Node.js, designed to provide basic math operations and a greeting resource for AI assistants and tool integrations.
Features
- Addition, Subtraction, Multiplication, Division (with division-by-zero error handling)
- Square and Square Root (with error handling for negative input, and results rounded to two decimals)
- Greatest Common Measure (GCM) and Least Common Multiple (LCM)
- Greeting resource (returns a personalized greeting)
- Fully type-safe using Zod schemas
- Easily extensible for more tools/resources
Installation
- Clone the repository or copy the project files.
- Install dependencies:
npm install - Compile the TypeScript code:
npx tsc
Running the Server
This project is designed to run as an MCP server using VS Code's MCP integration.
- Ensure your
.vscode/mcp.jsonis configured as follows:{ "servers": { "my-mcp-server-d95b22f0": { "type": "stdio", "command": "node", "args": ["d:/Proj/3/mcp-demo/dist/index.js"] } }, "inputs": [] } - Start VS Code and ensure the MCP extension is enabled. The server will start automatically.
Available Tools
- add: Add two numbers
- Input:
{ a: number, b: number } - Output:
The sum of a and b is result
- Input:
- subtract: Subtract b from a
- Input:
{ a: number, b: number } - Output:
The difference of a and b is result
- Input:
- multiply: Multiply two numbers
- Input:
{ a: number, b: number } - Output:
The product of a and b is result
- Input:
- divide: Divide a by b
- Input:
{ a: number, b: number } - Output:
The quotient of a divided by b is result(error if b = 0)
- Input:
- square: Square a number
- Input:
{ a: number } - Output:
The square of a is result
- Input:
- sqrt: Square root of a number
- Input:
{ x: number } - Output:
The square root of x is result(rounded to two decimals, error if x < 0)
- Input:
- gcm: Greatest Common Measure of two numbers
- Input:
{ a: number, b: number } - Output:
The greatest common measure of a and b is result
- Input:
- lcm: Least Common Multiple of two numbers
- Input:
{ a: number, b: number } - Output:
The LCM of a and b is result
- Input:
Greeting Resource
- greet: Returns a greeting for a given name
- Resource URI:
greet://{name} - Output:
Hello, {name}!
- Resource URI:
Example Usage
- Add:
{ a: 2, b: 3 }→The sum of 2 and 3 is 5 - Subtract:
{ a: 10, b: 5 }→The difference of 10 and 5 is 5 - Multiply:
{ a: 4, b: 6 }→The product of 4 and 6 is 24 - Divide:
{ a: 8, b: 2 }→The quotient of 8 divided by 2 is 4 - Square:
{ a: 7 }→The square of 7 is 49 - Square Root:
{ x: 5 }→The square root of 5 is 2.24 - GCM:
{ a: 12, b: 18 }→The greatest common measure of 12 and 18 is 6 - LCM:
{ a: 2, b: 5 }→The LCM of 2 and 5 is 10 - Greeting:
greet://Alice→Hello, Alice!
Extending the Project
You can easily add more tools or resources by registering them in src/index.ts using the MCP SDK and Zod schemas.
License
MIT
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。