MCP Websocket Server

Provides an HTTP MCP data endpoint on port 8080 and a WebSocket push update channel on port 8765 for real-time data delivery.
  • python

28

GitHub Stars

python

Language

6 months ago

First Indexed

2 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

You run an MCP server that exposes data access over HTTP while also pushing real-time updates to clients via WebSocket. This combination lets clients fetch data on demand and subscribe to live changes as soon as new information becomes available, all handled efficiently with asynchronous I/O.

How to use

Connect your MCP client to the HTTP endpoint to perform standard requests and retrieve data as needed. Open a WebSocket connection to receive real-time push notifications whenever new data becomes available, and use the subscribe action to start receiving updates.

Key endpoints you will interact with are the HTTP MCP server on port 8080 for standard requests and the WebSocket MCP endpoint on port 8765 for live updates. Start by subscribing over WebSocket, then issue MCP requests over HTTP as your application needs.

To ensure you receive timely updates, keep the WebSocket connection alive and handle incoming messages as event-driven data. The architecture is asynchronous, which helps maintain responsiveness even as updates arrive rapidly.

# Start the servers (in a single terminal)
python server.py

# WebSocket endpoint for subscriptions
ws://localhost:8765

# MCP HTTP endpoint for data requests
http://localhost:8080

How to install

Prerequisites you need on your machine: Python 3.8+ and a modern package manager. You will install the required Python dependencies and then start the server.

Step 1: Install Python 3.8 or newer on your system. If you need to upgrade, use your operating system’s package manager or download from the official Python website.

Step 2: Create a project directory and install dependencies.

# Create project directory (optional)
mkdir mcp-websocket-server
cd mcp-websocket-server

# Install dependencies
pip install websockets mcp-sdk

Step 3: Start the servers.

python server.py

Configuration and usage notes

The server runs two endpoints: an MCP HTTP interface on port 8080 for standard requests, and a WebSocket interface on port 8765 for real-time subscriptions. Clients can subscribe to updates and receive push notifications whenever new data becomes available.

If you need to verify connectivity, you can check that the HTTP endpoint responds to MCP requests and that the WebSocket endpoint accepts subscription messages. Typical client behavior includes subscribing to updates and then making data requests as needed.

Available tools

subscribe

Connect to the WebSocket endpoint and subscribe to real-time updates so you receive push notifications when new data becomes available.

get_data

Send MCP requests to the HTTP server to retrieve data or perform actions supported by the MCP API.

push_notifications

Automatic delivery of updates to all subscribed clients whenever new data becomes available.

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