MCP Server Research

Provides a basic MCP server demo with client data exchange, heartbeat handling, routing, and a web dashboard
  • python

0

GitHub Stars

python

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

MCP enables distributed systems to coordinate actions through a standardized, message-based protocol. This server demo showcases a simple MCP server that tracks connected clients, processes heartbeat and data messages, routes communications, and provides a web dashboard to monitor activity, all with in-memory history for easy testing.

How to use

You can use the MCP server with a client that supports the protocol. Start the server with default settings, then run a client demo to see the flow of messages between the server and a client. You can also customize the server port and enable debugging to aid development.

How to install

Prerequisites: Python 3.8 or newer, Flask, and Requests.

Clone the project, set up a virtual environment, install dependencies, and run the demo.

# Clone the repository
git clone https://github.com/ckz/mcp_server_research.git
cd mcp_server_research

# Set up virtual environment
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install -r requirements.txt

How to run the demo

Start the MCP server with default settings and then view the dashboard at the port you specify.

cd src/demo
python simple_mcp_server.py

To customize settings, set environment variables before starting the server.

cd src/demo
DEBUG=true PORT=5001 python simple_mcp_server.py

Visit the dashboard in your browser at http://localhost:5001 (or your chosen port).

Run a client demo

Open another terminal to run a client demo that connects to your MCP server and sends messages for a defined duration and interval.

cd src/demo
python client_demo.py --server http://localhost:5001 --duration 30 --interval 2

Available tools

registerClient

Registers and tracks connected clients as they connect to the MCP server.

handleHeartbeat

Processes heartbeat messages to monitor liveness of clients.

routeMessage

Routes messages to the appropriate destinations or clients based on the MCP protocol.

dashboard

Provides a web-based dashboard to monitor system activity and message history.

messageHistory

Maintains an in-memory history of messages exchanged during the session.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational