MCP Math Server
Provides basic mathematical operations including arithmetic, square root, and number theory functions like GCD and LCM. Built with TypeScript and includes proper error handling for edge cases like division by zero.
README
MCP Math Server
A Model Context Protocol (MCP) server built with TypeScript and Node.js, designed to provide basic math operations and a greeting resource for AI assistants and tool integrations.
Features
- Addition, Subtraction, Multiplication, Division (with division-by-zero error handling)
- Square and Square Root (with error handling for negative input, and results rounded to two decimals)
- Greatest Common Measure (GCM) and Least Common Multiple (LCM)
- Greeting resource (returns a personalized greeting)
- Fully type-safe using Zod schemas
- Easily extensible for more tools/resources
Installation
- Clone the repository or copy the project files.
- Install dependencies:
npm install - Compile the TypeScript code:
npx tsc
Running the Server
This project is designed to run as an MCP server using VS Code's MCP integration.
- Ensure your
.vscode/mcp.jsonis configured as follows:{ "servers": { "my-mcp-server-d95b22f0": { "type": "stdio", "command": "node", "args": ["d:/Proj/3/mcp-demo/dist/index.js"] } }, "inputs": [] } - Start VS Code and ensure the MCP extension is enabled. The server will start automatically.
Available Tools
- add: Add two numbers
- Input:
{ a: number, b: number } - Output:
The sum of a and b is result
- Input:
- subtract: Subtract b from a
- Input:
{ a: number, b: number } - Output:
The difference of a and b is result
- Input:
- multiply: Multiply two numbers
- Input:
{ a: number, b: number } - Output:
The product of a and b is result
- Input:
- divide: Divide a by b
- Input:
{ a: number, b: number } - Output:
The quotient of a divided by b is result(error if b = 0)
- Input:
- square: Square a number
- Input:
{ a: number } - Output:
The square of a is result
- Input:
- sqrt: Square root of a number
- Input:
{ x: number } - Output:
The square root of x is result(rounded to two decimals, error if x < 0)
- Input:
- gcm: Greatest Common Measure of two numbers
- Input:
{ a: number, b: number } - Output:
The greatest common measure of a and b is result
- Input:
- lcm: Least Common Multiple of two numbers
- Input:
{ a: number, b: number } - Output:
The LCM of a and b is result
- Input:
Greeting Resource
- greet: Returns a greeting for a given name
- Resource URI:
greet://{name} - Output:
Hello, {name}!
- Resource URI:
Example Usage
- Add:
{ a: 2, b: 3 }→The sum of 2 and 3 is 5 - Subtract:
{ a: 10, b: 5 }→The difference of 10 and 5 is 5 - Multiply:
{ a: 4, b: 6 }→The product of 4 and 6 is 24 - Divide:
{ a: 8, b: 2 }→The quotient of 8 divided by 2 is 4 - Square:
{ a: 7 }→The square of 7 is 49 - Square Root:
{ x: 5 }→The square root of 5 is 2.24 - GCM:
{ a: 12, b: 18 }→The greatest common measure of 12 and 18 is 6 - LCM:
{ a: 2, b: 5 }→The LCM of 2 and 5 is 10 - Greeting:
greet://Alice→Hello, Alice!
Extending the Project
You can easily add more tools or resources by registering them in src/index.ts using the MCP SDK and Zod schemas.
License
MIT
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.