Advertise
MCP.so
Sign In

MCP Signaling Server (Django + Channels + ASGI)

@yer-retb

Repository

Basic information

Category

Developer Tools

Transports

stdio

Author

yer-retb

About MCP Signaling Server

No overview available yet

MCP Signaling Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "Asynchronous-MCP-Server-with-WebRTC-Signaling": {
      "command": "python3",
      "args": [
        "-m",
        "venv",
        "venv"
      ]
    }
  }
}

MCP Signaling Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

What is MCP Signaling Server (Django + Channels + ASGI)?

An asynchronous backend WebSocket signaling server built with Django and Channels, implementing a custom protocol called MCP (Message Context Protocol) for real-time WebRTC signaling. It allows React frontend clients to exchange signaling messages without using REST APIs.

How to use MCP Signaling Server (Django + Channels + ASGI)?

Clone the repository, create a Python virtual environment, install dependencies from requirements.txt, then run the server using daphne mcp_server.asgi:application. Connect via WebSocket at ws://127.0.0.1:8000/ws/signal/?room=ROOM_NAME. A test script (test_mcp.py) is provided to simulate two clients.

Key features of MCP Signaling Server (Django + Channels + ASGI)

  • ASGI-compliant Django server with real-time WebSocket support
  • Custom signaling protocol: MCP (Message Context Protocol)
  • Room-based signaling (multi-user capable)
  • Supports offer, answer, candidate, and leave messages
  • Works with any frontend WebRTC client (React, etc.)
  • Includes test script for two-client simulation

Use cases of MCP Signaling Server (Django + Channels + ASGI)

  • Set up peer-to-peer video/audio chat with WebRTC signaling
  • Enable real-time messaging between two browser clients via WebRTC DataChannels
  • Test and develop custom WebRTC signaling logic with a lightweight backend
  • Create room-based applications where exactly two peers communicate directly
  • Demonstrate integration of Django Channels with WebSocket and WebRTC

Frequently asked questions

1

How many peers can join a room?

Only two peers are allowed per room. A third client is rejected by the backend and receives an error.

2

What are the runtime dependencies?

The server requires Python 3, Django, Channels, and Daphne (ASGI server). The frontend requires Node.js and npm.

3

Where are signaling rooms stored?

Rooms are kept in memory using Python dictionaries (in‑memory storage) for development simplicity.

4

What WebSocket transport does the server use?

The server uses ASGI via Daphne; clients connect using the `ws://` protocol (e.g., `ws://localhost:8000/ws/signal/?room=ROOM_NAME`).

5

Does the server include authentication or authorization?

The README does not mention any authentication mechanism; the signaling server appears to be open to any WebSocket connection.

Comments

More Developer Tools MCP servers

NextBlock CMS

NextBlock

Open-source Next.js + Supabase CMS with a per-site MCP server: scaffold a site, then create pages, posts, navigation, media and SEO from Claude, Cursor or any MCP client. Streamable HTTP with a bearer token you mint in y

Perfex CRM

themesic

Turn Perfex CRM into an AI-ready workspace. This MCP server exposes your full REST API to Claude, ChatGPT and any AI agent, so leads, invoices and tasks are one prompt away.

1

PuzzleTide Puzzle Generator

Caravaca-Labs

Word search generator, crossword generator, and sudoku generator + solver as a local-first MCP server. 15 deterministic tools: printable PDF puzzle worksheets, themed word banks, and verifiable LLM evals. From the makers

Heard

Heard

Let your cloud agents talk to you. Grok Bot, Meta Muse, ChatGPT, Claude, Devin and others report progress to Heard, which reads it out loud on your Mac, and they pick up the replies you send back.

GAIP Agents

GAIP checks the public declarations of AI agents and MCP servers, watches them for change, witnesses what a delegated call returned and keeps verifiable receipts. Free, read-only, no account or API key. Every result sta

Advertise