Stateless Math MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Stateless Math MCP ServerAdd the numbers 15 and 27 together"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Sample Application (Stateless Architecture)
A Model Context Protocol (MCP) sample project implemented in Python using FastMCP and mcp.client. This project demonstrates a stateless MCP server exposing mathematical tools over stdio transport along with an asynchronous client.
Features
Stateless MCP Server (
server.py): Uses standardstdiotransport without maintaining session states.Asynchronous Client (
client.py): Connects to the MCP server, discovers available tools dynamically, and executes tool calls.
Related MCP server: node-mcp-poc
Setup & Installation
Prerequisites
Python 3.10+ (Python 3.14 supported)
Virtual Environment (
.venv)
1. Create and Activate Virtual Environment
python3 -m venv .venv
source .venv/bin/activate2. Install Dependencies
pip install -r requirements.txtRunning the Application
Option A: Using the Runner Script
Execute the provided bash script to automatically use the environment's Python interpreter:
chmod +x run_sample.sh
./run_sample.shOption B: Running Manually
Activate your virtual environment and run the client:
python3 client.pyExample Output
When running client.py or ./run_sample.sh, the client will:
Start the MCP server via
stdio.Discover and print all available registered tools.
Invoke the
somatool with argumentsa=15andb=27.
Starting MCP Server (Stateless Mode 2026-07-28 Spec)...
Connected to MCP Server (Stateless Mode).
--- Discovered Tools (Stateless) ---
{
"name": "soma",
"description": "Soma dois números fornecidos pelo usuário statelessly.",
...
}
------------------------------------
Calling tool: soma(15, 27)...
Result: O resultado de 15.0 + 27.0 é 42.0
Client finished. Stateless server connection closed.This server cannot be deployed
Maintenance
Related MCP Connectors
MCP server for progressive tool usage at any scale (see https://klavis.ai)
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
Related MCP Servers
- FlicenseNot gradedqualityDmaintenanceA minimal reference implementation of an MCP server with two basic math tools (add and multiply), designed as a starting point for learning MCP protocol and deploying remote servers to cloud platforms.1-
- FlicenseNot gradedqualityDmaintenanceA minimal MCP server that exposes tools for addition, echoing text, time lookup, and URL fetching, with support for HTTP and stdio transports.-
- FlicenseNot gradedqualityCmaintenanceA model-agnostic MCP server exposing example tools (add1, multiply2, greet) for learning purposes, working with any LLM through stdio transport.-
- FlicenseAqualityCmaintenanceA learning-oriented MCP server that exposes basic tools (echo, add, reverse) over stdio transport to validate MCP handshake and tool calls.3-