Math Quiz

Provides a math evaluation service that computes expressions and returns precise results for use by LLM-assisted workflows.

typescript

0

GitHub Stars

typescript

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "jaffrepaul-mcp-math": {
      "command": "node",
      "args": [
        "${HOME}/path/to/mcp-math/mcp-server/dist/index.js"
      ]
    }
  }
}

This MCP server acts as a dedicated math coprocessor. It handles mathematical computations requested by an LLM or client, delivering accurate results by leveraging a robust math engine. By offloading calculations to this server, you gain precise, reliable math evaluation while keeping the model focused on interpretation and orchestration.

How to use

You can use the math MCP server with an MCP client such as Cursor or Claude Desktop. Start by configuring the client to connect to the local math server, then issue prompts that require calculations. The server exposes an evaluation capability that computes expressions and returns exact results, enabling seamless integration into your math-assisted workflows.

How to install

Prerequisites: Node.js 18 or newer, npm, and a compatible shell.

From the project root, install all dependencies.

npm install
cd frontend && npm install
cd ../mcp-server && npm install
cd ..

If you prefer a single command sequence, you can run the convenience script to install all dependencies.

npm run install:all

Build the MCP server before running the application.

cd mcp-server
npm run build

Start the frontend to use the quiz interface.

cd frontend
npm run dev

Additional configuration and usage notes

Configure the MCP client to locate and run the math server. The math server is started locally via a Node.js command that points to the compiled server script.

Cursor and Claude Desktop configuration blocks show how to wire the MCP server into the client. The following examples illustrate the required structure for both environments.

Examples of using the math server

Once configured, you can instruct the AI to perform calculations through the evaluate tool provided by the MCP server, such as evaluating arithmetic expressions, exponents, and common functions. The server executes the computation and returns the result for display in the frontend.

Notes and troubleshooting

The current frontend runs computations locally for demo purposes. In production, connect the frontend to Claude Desktop or Cursor so they can request calculations via the MCP server.

Security and maintenance considerations

Limit access to the MCP server to trusted clients, monitor usage, and ensure dependencies are kept up to date with security patches. When deploying, consider running the server behind an authentication layer if exposed beyond a localhost environment.

Development and production workflow

Development: modify the server or frontend, then rebuild the MCP server and restart the client to pick up changes.

Production: build both frontend and MCP server, then deploy to your hosting environment with proper process management and monitoring.

Available tools

evaluate

Evaluates a mathematical expression and returns the result. Supports basic arithmetic, exponents, parentheses, common math functions like sqrt, sin, cos, tan, log, and constants like pi and e.