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.
š Project Structure
The project is organized for scalability and readability:
.
āāā index.ts # Entry point: Initializes server and registers modules
āāā src/
ā āāā tools.ts # Tool handlers (Arithmetic, Randomness, Sampling)
ā āāā prompts.ts # Prompt templates (Math Tutoring)
ā āāā resources.ts # Resource definitions (System Status)
āāā tests/
ā āāā utility.test.ts # Comprehensive unit tests
āāā package.json # Dependencies and scripts
āāā tsconfig.json # TypeScript configuration
āāā jest.config.js # Testing configuration
š 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.
š” 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.
š 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
}
}
}
š 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"
}
}
š 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"
}
}
}
š Development
Setup
npm install
Running the Server
npm start
Running Tests
npm test
š¤ 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.
š 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.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.