Skip to content

Installation

Installation

mcmqtt is designed for instant execution with zero configuration. Choose the installation method that best fits your workflow.

The fastest way to run mcmqtt with no installation required:

Terminal window
# Run mcmqtt directly
uvx mcmqtt
# Run with specific options
uvx mcmqtt --transport http --port 8080
# Add to Claude Code MCP servers
claude mcp add task-buzz "uvx mcmqtt"

Benefits:

  • ✅ No installation or setup required
  • ✅ Always runs the latest version
  • ✅ Isolated execution environment
  • ✅ Perfect for testing and development

Traditional Installation

Terminal window
# Install mcmqtt
uv add mcmqtt
# Or install globally
uv tool install mcmqtt
# Run mcmqtt
mcmqtt

Using pip

Terminal window
# Install from PyPI
pip install mcmqtt
# Or install from source
pip install git+https://git.supported.systems/MCP/mcmqtt.git
# Run mcmqtt
mcmqtt

Using pipx (Isolated Installation)

Terminal window
# Install in isolated environment
pipx install mcmqtt
# Run mcmqtt
mcmqtt

Development Installation

For contributing to mcmqtt or customizing functionality:

Terminal window
# Clone the repository
git clone https://git.supported.systems/MCP/mcmqtt.git
cd mcmqtt
# Install in development mode with uv
uv sync --dev
# Or with pip
pip install -e ".[dev]"
# Run tests
pytest
# Run mcmqtt
python -m mcmqtt

Container Deployment

Docker

Run mcmqtt in a container for production deployments:

Terminal window
# Build the image
docker build -t mcmqtt .
# Run basic container
docker run -p 8080:8080 mcmqtt --transport http
# Run with environment configuration
docker run -p 8080:8080 \
-e MQTT_BROKER_HOST=mqtt.example.com \
-e MQTT_BROKER_PORT=1883 \
mcmqtt

Docker Compose

For production deployments with MQTT brokers:

docker-compose.yml
version: '3.8'
services:
mcmqtt:
build: .
ports:
- "8080:8080"
environment:
- MQTT_BROKER_HOST=mosquitto
- MQTT_BROKER_PORT=1883
depends_on:
- mosquitto
mosquitto:
image: eclipse-mosquitto:2
ports:
- "1883:1883"
volumes:
- ./mosquitto.conf:/mosquitto/config/mosquitto.conf
Terminal window
# Start the stack
docker compose up -d
# Check status
docker compose ps
# View logs
docker compose logs mcmqtt

System Requirements

Minimum Requirements

  • Python: 3.11 or higher
  • Memory: 256MB RAM
  • Storage: 100MB disk space
  • Network: Internet connection for PyPI packages
  • Python: 3.12+ for best performance
  • Memory: 1GB+ RAM for agent swarms
  • Storage: 1GB+ for logs and temporary files
  • CPU: 2+ cores for concurrent operations

Platform Support

PlatformSupport LevelNotes
Linux✅ FullPrimary development platform
macOS✅ FullIntel and Apple Silicon
Windows✅ FullWSL2 recommended
Docker✅ FullCross-platform containers

Verification

After installation, verify mcmqtt is working correctly:

Terminal window
# Check version
mcmqtt --version
# or
uvx mcmqtt --version
# Expected output:
# mcmqtt v2025.09.17 - FastMCP MQTT Server
# Test basic functionality
mcmqtt --help
# Start in test mode
mcmqtt --test-mode

MCP Integration

Claude Code Setup

Add mcmqtt to your Claude Code configuration:

Terminal window
# Add mcmqtt as MCP server
claude mcp add task-buzz "uvx mcmqtt"
# Test the connection
claude mcp test task-buzz
# List all MCP servers
claude mcp list
# Expected output:
# ✅ task-buzz: uvx mcmqtt (connected)

Custom MCP Configuration

For advanced setups, create a custom MCP configuration:

{
"mcpServers": {
"mcmqtt-prod": {
"command": "uvx",
"args": ["mcmqtt", "--broker", "mqtt://prod-broker:1883"],
"env": {
"MQTT_CLIENT_ID": "production-client",
"LOG_LEVEL": "INFO"
}
},
"mcmqtt-dev": {
"command": "uvx",
"args": ["mcmqtt", "--transport", "http", "--port", "8080"],
"env": {
"LOG_LEVEL": "DEBUG"
}
}
}
}

Environment Configuration

Environment Variables

Configure mcmqtt behavior with environment variables:

Terminal window
# Broker connection
export MQTT_BROKER_HOST="mqtt.example.com"
export MQTT_BROKER_PORT="1883"
export MQTT_USERNAME="username"
export MQTT_PASSWORD="password"
# Client settings
export MQTT_CLIENT_ID="mcmqtt-server"
export MQTT_KEEPALIVE="60"
export MQTT_QOS_DEFAULT="1"
# Server settings
export MCMQTT_TRANSPORT="stdio" # or "http"
export MCMQTT_PORT="8080"
export LOG_LEVEL="INFO"
# Agent coordination
export AGENT_ISOLATION="container"
export AGENT_MEMORY_LIMIT="512MB"
export AGENT_CPU_LIMIT="0.5"
# Run with environment config
uvx mcmqtt

Configuration File

Create a configuration file for complex setups:

mcmqtt.yaml
server:
transport: stdio
port: 8080
log_level: INFO
mqtt:
broker:
host: mqtt.example.com
port: 1883
username: user
password: pass
client:
id: mcmqtt-server
keepalive: 60
clean_session: true
agents:
isolation: container
resources:
memory: 512MB
cpu: 0.5
disk: 1GB
coordination:
pattern: worker-pool
health_check_interval: 30
Terminal window
# Use configuration file
uvx mcmqtt --config mcmqtt.yaml

Troubleshooting Installation

Common Issues

Python Version Error

Terminal window
# Error: Python 3.11+ required
python --version
# Solution: Install Python 3.11+
# On Ubuntu/Debian:
sudo apt update && sudo apt install python3.11
# On macOS:
brew install python@3.11
# On Windows:
# Download from python.org

Permission Errors

Terminal window
# Error: Permission denied
# Solution: Use user installation
pip install --user mcmqtt
# Or use pipx for isolation
pipx install mcmqtt

Network/Firewall Issues

Terminal window
# Error: Connection timeout
# Solution: Check firewall and proxy settings
# Test connectivity
curl -I https://pypi.org/simple/mcmqtt/
# Configure proxy if needed
pip install --proxy http://proxy.example.com:8080 mcmqtt

Missing Dependencies

Terminal window
# Error: ModuleNotFoundError
# Solution: Install with all dependencies
pip install mcmqtt[all]
# Or install specific extras
pip install mcmqtt[dev,test]

Diagnostic Commands

Terminal window
# Check Python environment
python -m mcmqtt --diagnose
# Check MQTT connectivity
uvx mcmqtt --test-mqtt mqtt://test.mosquitto.org:1883
# Check container support
uvx mcmqtt --test-containers
# Generate system report
uvx mcmqtt --system-report

Upgrading

Upgrade with uvx

Terminal window
# uvx automatically uses latest version
uvx mcmqtt # Always runs latest

Upgrade Traditional Installation

Terminal window
# With uv
uv tool upgrade mcmqtt
# With pip
pip install --upgrade mcmqtt
# With pipx
pipx upgrade mcmqtt

Version Pinning

Terminal window
# Pin to specific version
pip install mcmqtt==2025.09.17
# Or use version constraints
pip install "mcmqtt>=2025.09.17,<2026"

Next Steps

Once mcmqtt is installed:

  1. Quick Start - Get running in 2 minutes
  2. Configuration - Customize for your needs
  3. First Connection - Make your first MQTT connection
  4. Agent Coordination - Explore fractal agent capabilities

Installation is just the beginning. mcmqtt’s real power emerges when you start coordinating AI agents across distributed systems. 🚀