Skip to main content
Glama
amandhunna

MCP Calculator Service

by amandhunna

MCP Calculator Service

A Model-Context-Protocol (MCP) implementation for a calculator service that uses Claude AI to process natural language requests and perform mathematical calculations.

Architecture

The service consists of three main components:

  1. Calculator API (calculator-api.js): Handles basic mathematical operations

  2. MCP Server (mcp-server.js): Manages LLM integration and tool orchestration

  3. MCP Client (mcp-client.js): Provides a user interface for interacting with the service

Related MCP server: Calculator MCP

Setup

  1. Install dependencies:

npm install
  1. Create a .env file in the root directory with the following variables:

ANTHROPIC_API_KEY=your_api_key_here
PORT=3000
MCP_PORT=3001

Running the Service

You can run all components concurrently:

npm start

Or run them individually:

# Calculator API
npm run start:calculator

# MCP Server
npm run start:mcp

# MCP Client
npm run start:client

Usage

Once the service is running, you can interact with it through the client interface. Here are some example commands:

  • "Add 5 and 3"

  • "What is 10 plus 20?"

  • "Calculate 7.5 + 2.25"

  • "Multiply 4 by 6"

  • "What is 8 times 3?"

Type "help" for more examples or "exit" to quit.

API Endpoints

Calculator API (Port 3000)

  • POST /:operation - Perform mathematical operations (add, subtract, multiply, divide, power)

  • GET /health - Health check endpoint

MCP Server (Port 3001)

  • GET /tools - List available tools

  • POST /execute/:toolId - Execute a specific tool

  • POST /agent - Process natural language requests

  • GET /health - Health check endpoint

Error Handling

The service includes comprehensive error handling for:

  • Invalid mathematical operations

  • Division by zero

  • Invalid parameter types

  • LLM response parsing errors

  • Network errors

Dependencies

  • @anthropic-ai/sdk: ^0.51.0

  • axios: ^1.6.7

  • body-parser: ^1.20.2

  • cors: ^2.8.5

  • dotenv: ^16.4.5

  • express: ^4.18.3

  • concurrently: ^8.2.2 (dev dependency)

A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    A
    quality
    B
    maintenance
    A Model Context Protocol server that provides basic mathematical and statistical functions to LLMs, enabling them to perform accurate numerical calculations through a simple API.
    2
    13
    38
    170
    MIT
  • A
    license
    B
    quality
    C
    maintenance
    A Model Context Protocol server that provides basic calculator functionality for LLMs, enabling them to perform mathematical operations like addition, subtraction, multiplication, division, modulo, and square root.
    6
    360
    16
    MIT
  • A
    license
    -
    quality
    D
    maintenance
    A backend service that provides accurate arithmetic calculation capabilities to AI models via the Model Context Protocol, allowing LLMs to offload mathematical computations for numerical queries.
    1
    MIT
  • A
    license
    B
    quality
    D
    maintenance
    A simple Model Context Protocol (MCP) server that provides basic calculation functions to Claude. It enables users to perform mathematical operations like addition directly through natural language commands.
    1
    MIT

View all related MCP servers

Related MCP Connectors

  • Hosted MCP server for LLM cost estimation, model comparison, and budget-aware routing.

  • A paid remote MCP for Pydantic AI structured output, built to return verdicts, receipts, usage logs,

  • A paid remote MCP for OpenAI Codex context compressor, built to return verdicts, receipts, usage log

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/amandhunna/mcpserver'

If you have feedback or need assistance with the MCP directory API, please join our Discord server