Calculator MCP Server

Calculator MCP Server

Provides basic calculator operations (add, subtract, multiply, divide) as MCP tools for use with Claude Desktop and other MCP clients.

Category
访问服务器

README

Calculator MCP Server

A simple Model Context Protocol (MCP) server that provides basic calculator operations as tools for Claude Desktop and other MCP clients.

Features

  • Add: Sum two numbers
  • Subtract: Find the difference between two numbers
  • Multiply: Calculate the product of two numbers
  • Divide: Divide numbers with proper zero-division handling

All operations support integers, floating-point numbers, and negative numbers.

Installation

Prerequisites

  • Python 3.10 or higher
  • pip (Python package manager)

Steps

  1. Clone or download this repository
git clone https://github.com/snedea/calc-mcp-server.git
cd calc-mcp-server
  1. Install dependencies
pip install -r requirements.txt

This installs:

  • fastmcp>=2.0.0 - MCP framework
  • pytest>=7.0.0 - Testing framework

Usage

Testing the Server

Run the server standalone to verify it works:

python3 calc_server.py

You should see:

🧮 Calculator MCP Server Starting

📋 Available tools:
   - add(a, b): Add two numbers
   - subtract(a, b): Subtract b from a
   - multiply(a, b): Multiply two numbers
   - divide(a, b): Divide a by b (handles zero)

💡 Configure in Claude Desktop to use these tools!

Press Ctrl+C to stop the server.

Configuring in Claude Desktop

To use these calculator tools in Claude Desktop:

  1. Locate your Claude Desktop config file:

    • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
    • Windows: %APPDATA%\Claude\claude_desktop_config.json
  2. Edit the config file (create it if it doesn't exist):

{
  "mcpServers": {
    "calculator": {
      "command": "python3",
      "args": ["/absolute/path/to/calc-mcp-server/calc_server.py"]
    }
  }
}

Important: Replace /absolute/path/to/calc-mcp-server/ with the actual full path to this directory.

  1. Restart Claude Desktop

The calculator tools will now be available! Claude can use them automatically when you ask questions involving calculations.

Available Tools

add(a, b)

Add two numbers together.

Parameters:

  • a (float): First number
  • b (float): Second number

Returns: JSON with operation details and result

Example:

Input: add(5, 3)
Output: {
  "operation": "add",
  "a": 5,
  "b": 3,
  "result": 8
}

subtract(a, b)

Subtract the second number from the first.

Parameters:

  • a (float): Number to subtract from
  • b (float): Number to subtract

Returns: JSON with operation details and result

Example:

Input: subtract(10, 3)
Output: {
  "operation": "subtract",
  "a": 10,
  "b": 3,
  "result": 7
}

multiply(a, b)

Multiply two numbers together.

Parameters:

  • a (float): First number
  • b (float): Second number

Returns: JSON with operation details and result

Example:

Input: multiply(4, 5)
Output: {
  "operation": "multiply",
  "a": 4,
  "b": 5,
  "result": 20
}

divide(a, b)

Divide the first number by the second.

Parameters:

  • a (float): Numerator
  • b (float): Denominator

Returns: JSON with operation details and result, or error if dividing by zero

Example:

Input: divide(10, 2)
Output: {
  "operation": "divide",
  "a": 10,
  "b": 2,
  "result": 5
}

Input: divide(10, 0)
Output: {
  "error": "Cannot divide by zero"
}

Testing

Run the test suite to verify all operations work correctly:

pytest tests/test_calculator.py -v

Expected output:

tests/test_calculator.py::TestAddition::test_add_positive_numbers PASSED
tests/test_calculator.py::TestAddition::test_add_negative_numbers PASSED
... (30+ tests)
================================ 30 passed in 0.XX s ================================

All tests should pass, covering:

  • Basic arithmetic operations
  • Edge cases (zero, negatives, decimals)
  • Error handling (division by zero)
  • JSON response format validation

Project Structure

calc-mcp-server/
├── calc_server.py          # Main MCP server with calculator tools
├── requirements.txt        # Python dependencies
├── tests/
│   └── test_calculator.py  # Comprehensive unit tests
├── README.md               # This file
└── .gitignore              # Git exclusions

Troubleshooting

Tools don't appear in Claude Desktop

  • ✅ Check that the config file path is correct for your OS
  • ✅ Verify the args path is absolute (not relative)
  • ✅ Ensure Python 3.10+ is installed: python3 --version
  • ✅ Confirm FastMCP is installed: pip show fastmcp
  • ✅ Restart Claude Desktop completely

Import errors when running server

  • ✅ Install dependencies: pip install -r requirements.txt
  • ✅ Use Python 3.10 or higher
  • ✅ Consider using a virtual environment:
    python3 -m venv venv
    source venv/bin/activate  # On Windows: venv\Scripts\activate
    pip install -r requirements.txt
    

Tests failing

  • ✅ Ensure pytest is installed: pip install pytest
  • ✅ Run from the project root directory
  • ✅ Check Python version is 3.10+

Technologies Used

  • Python 3.10+: Modern Python with type hints
  • FastMCP 2.0+: Official MCP framework for Python
  • pytest: Testing framework

How It Works

MCP (Model Context Protocol) is a standard for connecting AI assistants like Claude to external tools and data sources. This server:

  1. Defines calculator operations as Python functions
  2. Decorates them with @mcp.tool() to expose them via MCP
  3. Communicates with Claude Desktop using standard input/output (stdio transport)
  4. Returns structured JSON responses for reliable parsing

Claude can then call these tools automatically when needed for calculations!

License

MIT

Contributing

Contributions welcome! Feel free to:

  • Report bugs
  • Suggest new calculator features
  • Improve documentation
  • Add more tests

Created By

🤖 Generated with Context Foundry - Autonomous Development Platform

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