mcpField
A
A simple calculator app using Model Context protocol

A simple calculator app using Model Context protocol

Local
github.com/KeerthiNingegowdaDeveloper Tools0Updated 78w ago
Repository

About A simple calculator app using Model Context protocol

A small Python calculator project for exploring MCP tool calling and building a server-client pair. It supports basic arithmetic and uses an MCP client that turns user queries into operations.

Key features

  1. 01Addition, subtraction, multiplication, division, modulo
  2. 02FastMCP calculator server
  3. 03MCP client for natural-language queries
  4. 04Server inspection with MCP Inspector

Use cases

  1. 01Learning MCP server and client basics
  2. 02Testing natural-language calculator requests

MCP support

Includes a FastMCP server that exposes calculator operations and an MCP client that connects to it to perform requested calculations.

#python#llms#anthropic-api#modelcontextprotocol

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

A simple calculator app using Model Context protocol

Purpose of this repo

To explore basic building blocks of MCP and intricacies of tool calling within MCP, from scratch. Keeping it as simple as possible without handling many edge cases. Understand how to build both MCP Server and clients.

Core Features
  • A calculator app to do add, subtract, multiply, divide and modulo
  • Debugging server using MCP Inspector
    • A MCP-based client that takes a query from the user to perform the above mentioned operations
    Future possibilities for quick concept exploration
  • Sequential tool calling
  • Storage of previous chat history is not supported to maintain simplicity
  • Input validation by server and/or client

    • 🚨 Most of the technolgies used in this repo like FastMCP, tool calling in anthropic and MCP itself are very recent. So there are some features in these technologies that are either not available or buggy. But the main goal is a simple exploration without using cursor or Claude Desktop 🚨

    MCP compliant Calculator Server

    Is built using FastMCP, due to its simplicty and automatic error handling. Points to remember:-

  • Always name the server either as mcp or server or app. Throws an error otherwise and is quite explicit
  • Annotations can be included as a future reference. Right now it is not supported in FastMCP for the version in uv.lock
    • MCP client

    Makes a connection to MCP server and should have access to LLM Would higly suggest to explore and inspect the objects returned when the model uses a tool and a genertic reponse Try to stress test giving numbers in different format. Eg:- Add 2 and 3 v/s Add two and three. Eg:- Try to use ambiguous and large numbers:- Add seven hundred thousand trillion with three hundred billion

    Workflow overview

    alt text

    To reproduce the working environment whre .toml file is located

    uv sync

    TO activate the working environment use

    source .venv/bin/activate

    To simply inspect the server

    Go to fastmcp_calculator_server folder and run
    mcp dev server.py alt_text

    Add your anthropic API key to .env file

    To run the whole MCP app

    Go to mcp_calculator/mcp_compliant_client and run
    python client.py <path to server.py>

    More about this on medium.

    Comments

    Markdown supported

    New to MCP?

    From what the protocol is to installing your first server, these answers cover most first questions.

    An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.