Skip to main content
Glama
anupamsharnagat

Simple MCP Demo

🚀 Simple MCP Demo

A comprehensive demonstration of a Model Context Protocol (MCP) server implemented in Python. This project showcases how to build a unified server that supports multiple transport mechanisms: Standard I/O (stdio), Server-Sent Events (SSE), and Streamable HTTP.


🛠️ Features

  • Multi-Transport Server: One server, three ways to connect.

  • add_numbers Tool: A functional example of a tool discovery and execution flow.

  • Reference Clients: Dedicated Python scripts for each transport type.

  • Inspector Ready: Fully compatible with the official MCP Inspector.


Related MCP server: MCP Boilerplate

📂 Project Structure

  • server.py: The core MCP server containing tool logic and transport routing.

  • client_stdio.py: Client for local subprocess communication (pipes).

  • client_sse.py: Client for web-based event streaming.

  • client_http.py: Client for stateful session-based HTTP streaming.

  • DOCUMENTATION.md: Detailed functional and technical specifications.

  • requirements.txt: Project dependencies.


🚀 Getting Started

1. Installation

Clone the repo and install the required packages:

pip install -r requirements.txt

The easiest way to test the server is using the official tool inspector:

npx @modelcontextprotocol/inspector python server.py

3. Run Reference Clients

Standard I/O (stdio)

python client_stdio.py

Server-Sent Events (SSE)

Terminal 1 (Start Server):

python server.py --transport sse

Terminal 2 (Run Client):

python client_sse.py

Streamable HTTP

Terminal 1 (Start Server):

python server.py --transport http

Terminal 2 (Run Client):

python client_http.py

📈 Protocol Flow

  1. Initialize: Client and Server exchange capabilities.

  2. List Tools: Client discovers the add_numbers tool.

  3. Call Tool: Client sends parameters (a, b) and receives the sum.


📝 Technical Details

For a deeper dive into the architecture, flow diagrams, and transport implementation details, see DOCUMENTATION.md.


Built with ❤️ using the Model Context Protocol

F
license - not found
-
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

  • F
    license
    C
    quality
    D
    maintenance
    A demonstration server based on Model Context Protocol (MCP) that showcases how to build custom tools for AI assistants, providing mathematical calculation and multilingual greeting capabilities.
    Last updated
    3
  • F
    license
    -
    quality
    D
    maintenance
    A demonstration server designed to showcase core Model Context Protocol (MCP) primitives including tools, resources, and prompts for presentations. It provides functional examples like text analysis and financial calculations to illustrate how AI models interact with external functions and data.
    Last updated
    5
  • F
    license
    B
    quality
    D
    maintenance
    A demonstration MCP server providing basic tools for returning greetings and performing mathematical addition. It serves as a practical workshop guide for setting up and configuring Model Context Protocol servers from scratch using Python.
    Last updated
    2
    4

View all related MCP servers

Related MCP Connectors

  • A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…

  • A Model Context Protocol server for Wix AI tools

  • AI Reasoning Cache & Consensus Layer with 11 MCP tools via Streamable HTTP.

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/anupamsharnagat/mcpdemo'

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