Utility MCP Server
A TypeScript-based MCP server providing utility tools like arithmetic calculations, random number generation, and math tutoring prompts. It enables users to perform basic computational tasks and access system status resources through JSON-RPC 2.0 protocol.
README
Utility MCP Server
A fully featured Model Context Protocol (MCP) server providing utility tools, resources, and prompts. Built with TypeScript and the modern MCP SDK.
📁 Project Structure
The project is organized for scalability and readability:
.
├── index.ts # Entry point: Initializes server and registers modules
├── src/
│ ├── tools.ts # Tool handlers (Arithmetic, Randomness, Sampling)
│ ├── prompts.ts # Prompt templates (Math Tutoring)
│ └── resources.ts # Resource definitions (System Status)
├── tests/
│ └── utility.test.ts # Comprehensive unit tests
├── package.json # Dependencies and scripts
├── tsconfig.json # TypeScript configuration
└── jest.config.js # Testing configuration
🚀 Features
1. Tools
random_number: Generates a random integer within a specified range.calculator: Performs basic arithmetic (add,subtract,multiply,divide).suggest_arithmetic_task: Demonstrates LLM Sampling by requesting the client/LLM to generate a creative math problem.
2. Resources
system_status(utility://system/status): Provides a real-time status update of the server's health and feature count.
3. Prompts
math_tutor: A template that guides the LLM to act as a math teacher, optionally focusing on a specific topic.
📡 Calling the API (Postman / JSON-RPC)
Model Context Protocol uses JSON-RPC 2.0. While this server currently runs over stdio (standard input/output), you can interact with it using these message formats if you expose it via an HTTP/SSE bridge or use a debugger.
🛠 Tools
List Tools
Request:
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/list"
}
Call calculator
Request:
{
"jsonrpc": "2.0",
"id": 2,
"method": "tools/call",
"params": {
"name": "calculator",
"arguments": {
"operation": "multiply",
"a": 5,
"b": 10
}
}
}
📖 Resources
List Resources
Request:
{
"jsonrpc": "2.0",
"id": 3,
"method": "resources/list"
}
Read system_status
Request:
{
"jsonrpc": "2.0",
"id": 4,
"method": "resources/read",
"params": {
"uri": "utility://system/status"
}
}
📝 Prompts
List Prompts
Request:
{
"jsonrpc": "2.0",
"id": 5,
"method": "prompts/list"
}
Get math_tutor Prompt
Request:
{
"jsonrpc": "2.0",
"id": 6,
"method": "prompts/get",
"params": {
"name": "math_tutor",
"arguments": {
"topic": "algebra"
}
}
}
🛠 Development
Setup
npm install
Running the Server
npm start
Running Tests
npm test
🤖 Using the Custom Client
We've included a built-in client example so you can see how to connect programmatically:
npm run client
This script will:
- Spawn the server as a child process.
- Connect via Stdio.
- Automatically demonstrate listing tools, calling the calculator, and reading resources.
🔍 Testing with MCP Inspector
To interact with the server visually:
npx @modelcontextprotocol/inspector npx tsx index.ts
[!IMPORTANT] This server uses the Stdio Transport. It communicates via
stdinandstdout. For Postman to work via HTTP, an SSE (Server-Sent Events) transport layer would need to be added to the server configuration.
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。