Math MCP Server
Enables LLMs to perform accurate mathematical calculations by evaluating expressions using mathjs. Supports basic arithmetic, functions, constants, and complex mathematical operations through natural language requests.
README
Math Quiz with MCP Server
A demonstration application showing how an MCP (Model Context Protocol) server can act as a mathematical coprocessor. The LLM decides what calculations to perform, and the MCP server handles the computation using mathjs.
Architecture
- Frontend: React + Vite + Tailwind CSS - Simple math quiz interface
- MCP Server: Node.js + TypeScript - Mathematical evaluation service
Project Structure
mcp-math/
├── frontend/ # React quiz application
│ ├── src/
│ │ ├── App.tsx # Main quiz component
│ │ ├── main.tsx # React entry point
│ │ └── index.css # Tailwind styles
│ └── package.json
├── mcp-server/ # MCP server for math operations
│ ├── src/
│ │ └── index.ts # MCP server implementation
│ └── package.json
└── package.json # Workspace root
Setup Instructions
1. Install Dependencies
From the root directory:
npm install
cd frontend && npm install
cd ../mcp-server && npm install
cd ..
Or use the convenience script:
npm run install:all
2. Build the MCP Server
cd mcp-server
npm run build
3. Configure MCP Client
For Cursor
Add the MCP server to your Cursor configuration file:
Location: ~/.cursor/mcp.json
Example configuration:
{
"mcpServers": {
"math": {
"command": "node",
"args": ["${HOME}/path/to/mcp-math/mcp-server/dist/index.js"]
}
}
}
Important: Replace path/to/mcp-math with the actual path from your home directory to your project directory. The ${HOME} variable will be automatically expanded.
After updating the configuration, restart Cursor for the changes to take effect.
For Claude Desktop
Add the MCP server to your Claude Desktop configuration file:
MacOS/Linux: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Example configuration:
{
"mcpServers": {
"math": {
"command": "node",
"args": ["${HOME}/path/to/mcp-math/mcp-server/dist/index.js"]
}
}
}
Important: Replace path/to/mcp-math with the actual path from your home directory to your project directory.
After updating the configuration, restart Claude Desktop for the changes to take effect.
Running the Application
Start the Frontend
cd frontend
npm run dev
The quiz app will be available at http://localhost:5173
Using the MCP Server with Claude/Cursor
Once configured, you can ask Claude (or Cursor AI) to use the math server:
Example prompts:
- "Use the math server to calculate 123 * 456"
- "Evaluate sqrt(144) + sin(pi/2) using the evaluate tool"
- "What is (25 + 75) / (10 - 5)?"
The AI will automatically use the evaluate tool from the MCP server to perform calculations.
MCP Server Tools
evaluate
Evaluates a mathematical expression and returns the result.
Input:
expression(string): Mathematical expression to evaluate
Supported Operations:
- Basic arithmetic:
+,-,*,/ - Exponents:
^or** - Parentheses:
(,) - Common functions:
sqrt(),sin(),cos(),tan(),log(), etc. - Constants:
pi,e
Example:
{
"expression": "2 * (3 + 4)"
}
Response:
{
"expression": "2 * (3 + 4)",
"result": "14",
"success": true
}
Development
Frontend Development
npm run dev:frontend
MCP Server Development
After making changes to the MCP server:
cd mcp-server
npm run build
Then restart Claude Desktop to load the updated server.
Build for Production
# Build frontend
npm run build:frontend
# Build MCP server
npm run build:mcp
How It Works
The MCP Pattern
This application demonstrates the "coprocessor" pattern:
- Frontend displays math problems to users
- LLM (Claude) understands user intent and decides what calculations to perform
- MCP Server executes the calculations accurately using mathjs
- Result flows back through Claude to the application
Why Use MCP for Math?
- Accuracy: LLMs can struggle with precise calculations. The MCP server uses mathjs for exact results.
- Separation of Concerns: The LLM focuses on understanding and orchestration, while the MCP server handles computation.
- Extensibility: Easy to add new mathematical operations without retraining the model.
Notes
- The current frontend implementation calculates answers locally for demo simplicity
- In a production setup, you would connect the frontend to Claude (via API or desktop app) which would use the MCP server
- This is a demonstration project showing MCP architecture - not production-ready
Future Enhancements
Potential improvements:
- Add database for storing quiz results
- Connect frontend directly to Claude API with MCP
- Add more quiz types (algebra, geometry, etc.)
- Implement user authentication and progress tracking
- Add difficulty levels and adaptive quizzing
Troubleshooting
MCP Server not showing in Claude/Cursor
- Check the configuration file path is correct (
~/.cursor/mcp.jsonfor Cursor) - Ensure the path to
index.jsis correct (use${HOME}/...for portability) - Verify the server builds without errors:
cd mcp-server && npm run build - Check logs:
- Claude Desktop: Help → Show Logs
- Cursor: Check the MCP server output in Cursor settings
- Restart Claude Desktop or Cursor after configuration changes
Frontend not starting
- Ensure dependencies are installed:
cd frontend && npm install - Check Node.js version (requires Node 18+)
- Try clearing node_modules and reinstalling
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。