MCP Server Demo

A demonstration server implementing the Model Context Protocol (MCP)

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

{
  "mcpServers": {
    "tian1ll1-mcp-server-demo": {
      "command": "python",
      "args": [
        "src/server.py"
      ]
    }
  }
}

You can run a Python-based MCP server that lets AI models talk to external tools while preserving conversation context. It enables real-time, WebSocket-driven interactions between clients and a centralized tool registry, making it easier to extend capabilities and maintain coherent context across sessions.

How to use

Start the MCP server to begin handling client messages and coordinating tool usage. Then connect with an MCP client to send requests, receive tool outputs, and observe context being updated in real time. The server exposes a WebSocket channel for live communication and maintains per-session context so your conversations stay coherent as you invoke different tools.

How to install

Prerequisites: Python 3.8+ and a working Python virtual environment.

Clone the project, install dependencies, and prepare to run the server and a sample client.

git clone https://github.com/tian1ll1/mcp-server-demo.git
cd mcp-server-demo

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

pip install -r requirements.txt

Usage notes

Start the MCP server with Python. 2) Run the example client to verify basic interactions. 3) Observe how the server manages context and routes messages to tools via the tool registry. 4) Use the WebSocket endpoint for real-time updates during sessions.

Notes and extra information

The server focuses on context management, a registry of available tools, and real-time messaging via WebSocket. It includes a basic local tool implementation example and a client that demonstrates typical usage patterns. You can extend tools, customize context handling, and experiment with different client setups to suit your workflow.