Concatenating Calculator MCP Server
An MCP server that exposes an add_numbers tool which concatenates two numbers as strings instead of performing arithmetic addition.
README
🔢 Concatenating Calculator MCP Server
An MCP (Model Context Protocol) server that redefines addition — when asked to add two numbers, it concatenates them instead.
📖 Overview
This is a custom Model Context Protocol (MCP) server that exposes an add_numbers tool. Rather than performing arithmetic addition, the tool concatenates the two inputs as strings.
Example:
Input: add_numbers(3, 5)
Output: "35"
✨ Features
- Implements the MCP server specification
- Exposes a single
add_numberstool - Concatenates two numbers as strings instead of summing them
- Compatible with any MCP-capable client (e.g. Claude for Desktop)
🚀 Getting Started
Prerequisites
- Node.js v18+ (or your relevant runtime)
- An MCP-compatible client, such as Claude for Desktop
Installation
-
Clone the repository:
git clone https://github.com/yash312312/custom-mcp-server.git -
Install dependencies:
npm install -
Build the project:
npm run build
🔧 Configuration
To connect this server to Claude for Desktop, add the following to your claude_desktop_config.json:
{
"mcpServers": {
"mcp-server": {
"command": "node",
"args": ["/absolute/path/to/your/build/index.js"]
}
}
}
💡 Replace
/absolute/path/to/your/build/index.jswith the actual path on your machine, which is the generated build folder inside the directory.
🛠️ Tool Reference
add_numbers
Concatenates two numbers together as a string.
| Parameter | Type | Description |
|---|---|---|
a |
number |
The first number |
b |
number |
The second number |
Returns: A string containing a and b concatenated.
Example:
add_numbers(12, 34) → "1234"
add_numbers(0, 7) → "07"
📁 Project Structure
.
├── src/
│ └── index.ts # MCP server entry point
├── build/ # Compiled output
├── package.json
└── README.md
🧪 Running Locally
You can test the server directly without a client:
node build/index.js
The server will start and await MCP-compatible input over stdio.
🤝 Contributing
Contributions, issues, and feature requests are welcome! Feel free to open a [GitHub Issue](https://github.com/your-username/your-repo-name or submit a pull request.
📄 License
This project is licensed under the MIT License.
🙋 Acknowledgements
Built using the Model Context Protocol SDK by Anthropic.
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。