Power Switch Pro MCP Server
MCP server for controlling and monitoring Digital Loggers Power Switch Pro devices, enabling outlet control, power monitoring, and device management through natural language.
README
Power Switch Pro MCP Server
An MCP (Model Context Protocol) server that provides tools for controlling and monitoring Digital Loggers Power Switch Pro devices. This allows AI assistants and other MCP clients to interact with your power switch hardware.
Features
- š Outlet Control - Turn outlets on/off/cycle individually or in bulk
- š Power Monitoring - Read real-time voltage, current, power, and energy metrics
- š Device Management - Get device info and configure outlet names
- š Secure - Uses HTTP Digest Authentication via environment variables
- š Easy Integration - Works with any MCP-compatible client (Warp, Claude Desktop, etc.)
- š Multiple Transports - Supports both stdio (local) and HTTP (remote) via MCP streamable-http transport
- š³ Docker Ready - Easy containerized deployment with docker-compose
Installation
Prerequisites
- Python 3.10 or higher
- A Digital Loggers Power Switch Pro device with firmware 1.7.0+
- Network access to your device
Install from Source
git clone https://github.com/bryankemp/power-switch-pro-mcp.git
cd power-switch-pro-mcp
pip install .
Configuration
The MCP server is configured via environment variables:
POWER_SWITCH_HOST- IP address or hostname of your device (required)POWER_SWITCH_PASSWORD- Admin password (required)POWER_SWITCH_USERNAME- Username (default: "admin")POWER_SWITCH_USE_HTTPS- Use HTTPS instead of HTTP (default: "false")
For Warp
Add to your Warp MCP settings configuration file:
{
"mcpServers": {
"power-switch-pro": {
"command": "python",
"args": ["-m", "power_switch_pro_mcp.server"],
"env": {
"POWER_SWITCH_HOST": "192.168.0.100",
"POWER_SWITCH_PASSWORD": "your-password",
"POWER_SWITCH_USERNAME": "admin",
"POWER_SWITCH_USE_HTTPS": "false"
}
}
}
}
For Claude Desktop
Add to your Claude Desktop MCP settings (~/Library/Application Support/Claude/claude_desktop_config.json on macOS):
{
"mcpServers": {
"power-switch-pro": {
"command": "python",
"args": ["-m", "power_switch_pro_mcp.server"],
"env": {
"POWER_SWITCH_HOST": "192.168.0.100",
"POWER_SWITCH_PASSWORD": "your-password",
"POWER_SWITCH_USERNAME": "admin"
}
}
}
}
Note: POWER_SWITCH_USERNAME is optional and defaults to "admin" if not specified.
For Other MCP Clients
Refer to your MCP client's documentation for how to configure external MCP servers. You'll need to:
- Set the command to run:
python -m power_switch_pro_mcp.server - Configure the required environment variables
Available Tools
The server exposes the following MCP tools:
Outlet Control
-
outlet_on- Turn on a specific outlet- Parameters:
outlet_id(0-7)
- Parameters:
-
outlet_off- Turn off a specific outlet- Parameters:
outlet_id(0-7)
- Parameters:
-
outlet_cycle- Power cycle an outlet (off, wait, on)- Parameters:
outlet_id(0-7)
- Parameters:
-
bulk_outlet_operation- Perform operations on multiple outlets- Parameters:
action("on", "off", or "cycle"), optionaloutlet_idsarray
- Parameters:
Status and Monitoring
-
get_outlet_state- Get the power state of a specific outlet- Parameters:
outlet_id(0-7)
- Parameters:
-
get_all_outlet_states- Get power states of all outlets -
get_outlet_info- Get detailed info about an outlet (name, state, lock status)- Parameters:
outlet_id(0-7)
- Parameters:
-
get_power_metrics- Get real-time power measurements (voltage, current, power, energy) -
get_device_info- Get device information (serial, firmware version, etc.)
Configuration
set_outlet_name- Rename an outlet- Parameters:
outlet_id(0-7),name(string, max 16 chars)
- Parameters:
Usage Examples
Once configured, you can use natural language with your MCP client:
"Turn on outlet 3"
"What's the current power consumption?"
"Cycle the server outlet"
"Show me all outlet states"
"Rename outlet 0 to 'Lab Server'"
"Turn off all outlets"
Running the Server
Stdio Transport (Local)
For local MCP clients like Claude Desktop or Warp:
# Set environment variables
export POWER_SWITCH_HOST="192.168.0.100"
export POWER_SWITCH_PASSWORD="your-password"
export POWER_SWITCH_USERNAME="admin" # Optional, defaults to "admin"
# Run the stdio server
python -m power_switch_pro_mcp.server
The server will start and wait for MCP protocol messages on stdin/stdout.
HTTP Transport (Remote)
For remote access using the MCP streamable-http transport:
# Set environment variables
export POWER_SWITCH_HOST="192.168.0.100"
export POWER_SWITCH_PASSWORD="your-password"
export POWER_SWITCH_USERNAME="admin" # Optional, defaults to "admin"
# Run the HTTP server (default port 5000)
python -m power_switch_pro_mcp.http_server
# Or specify a custom port
PORT=3000 python -m power_switch_pro_mcp.http_server
The HTTP server will be available at http://localhost:5000 and supports the MCP streamable-http protocol.
Docker Deployment
Using Pre-built Image from GitHub Container Registry
The easiest way to run the server is using the pre-built Docker image:
# Pull the latest image
docker pull ghcr.io/bryankemp/power-switch-pro-mcp:latest
# Run the container
docker run -d \
-p 5000:5000 \
-e POWER_SWITCH_HOST="192.168.0.100" \
-e POWER_SWITCH_PASSWORD="your-password" \
-e POWER_SWITCH_USERNAME="admin" \
--name power-switch-pro-mcp \
ghcr.io/bryankemp/power-switch-pro-mcp:latest
Using Docker Compose (Recommended)
# Copy and configure environment variables
cp .env.docker .env
# Edit .env with your Power Switch Pro settings
# Start the server
docker-compose up -d
# View logs
docker-compose logs -f
# Stop the server
docker-compose down
Using Docker Directly
# Build the image
docker build -t power-switch-pro-mcp .
# Run the container
docker run -d \
-p 5000:5000 \
-e POWER_SWITCH_HOST="192.168.0.100" \
-e POWER_SWITCH_PASSWORD="your-password" \
-e POWER_SWITCH_USERNAME="admin" \
--name power-switch-pro-mcp \
power-switch-pro-mcp
# View logs
docker logs -f power-switch-pro-mcp
# Stop the container
docker stop power-switch-pro-mcp
CI/CD
This project uses GitHub Actions to automatically build and publish Docker images to GitHub Container Registry (ghcr.io).
Automated Docker Builds
Docker images are automatically built and published:
- On every push to main: Tagged as
latestandmain-{sha} - On version tags (e.g.,
v1.0.0): Tagged with semantic versions - On pull requests: Built but not published (for testing)
The workflow builds multi-platform images for:
linux/amd64(x86_64)linux/arm64(ARM64/Apple Silicon)
Available Tags
latest- Latest stable build from main branchv1.0.0,v1.0,v1- Semantic version tagsmain-{sha}- Specific commit from main branch
Development
Setting Up Development Environment
# Clone the repository
git clone https://github.com/bryankemp/power-switch-pro-mcp.git
cd power-switch-pro-mcp
# Install in editable mode with dev dependencies
pip install -e ".[dev]"
Code Quality
This project uses:
- Black - Code formatting (line length: 100)
- Ruff - Fast Python linting
- mypy - Static type checking
- pytest - Testing framework
- pre-commit - Git hooks for code quality
Run checks:
# Format code
black src
# Lint code
ruff check src
# Type check
mypy src
# Run all checks together
black src && ruff check src && mypy src
# Run tests
pytest
Git Hooks
The project includes automated git hooks for code quality and Docker testing:
Pre-commit Hooks
Automatically run on every commit:
- Black code formatting
- Ruff linting
- mypy type checking
- YAML/TOML validation
Pre-push Hook
Automatically run before every push:
- Docker image build test
- Container runtime verification
- HTTP endpoint health check
Installation
# Install pre-commit framework
pip install pre-commit
# Install all git hooks
pre-commit install
./hooks/install.sh
# Run hooks manually on all files
pre-commit run --all-files
Project Structure
power-switch-pro-mcp/
āāā src/
ā āāā power_switch_pro_mcp/
ā āāā __init__.py
ā āāā server.py # Stdio MCP server implementation
ā āāā http_server.py # HTTP MCP server implementation
āāā docs/ # Sphinx documentation
āāā tests/ # Test suite
āāā hooks/ # Git hooks
ā āāā pre-push # Pre-push hook (Docker testing)
ā āāā install.sh # Hook installation script
āāā Dockerfile # Docker container definition
āāā docker-compose.yml # Docker Compose configuration
āāā .pre-commit-config.yaml # Pre-commit hooks configuration
āāā pyproject.toml # Project configuration
āāā README.md # This file
āāā LICENSE # BSD-3-Clause license
āāā .env.example # Example environment configuration
āāā .env.docker # Docker environment template
Security Considerations
- Never commit credentials - Use environment variables or secure configuration
- Use HTTPS - Enable
POWER_SWITCH_USE_HTTPS=truewhen possible - Network Security - Ensure your power switch is on a secure network
- Access Control - Use the admin account or create restricted users on the device
Troubleshooting
Server won't start
- Check that environment variables are set correctly
- Verify you can reach the device at the configured host
- Ensure the password is correct
"Authentication Error"
- Double-check your username and password
- Verify the device firmware supports REST API (1.7.0+)
Tools not appearing in client
- Restart your MCP client after configuration changes
- Check the client's logs for MCP server errors
- Verify the server starts successfully in standalone mode
Related Projects
- power-switch-pro - The underlying Python library
- MCP Specification - Model Context Protocol documentation
License
BSD-3-Clause License - See LICENSE file for details
Author
Bryan Kemp (bryan@kempville.com)
Contributing
Contributions are welcome! Please:
- Fork the repository
- Create a feature branch
- Make your changes with tests
- Run code quality checks
- Submit a pull request
Support
- Issues: GitHub Issues
- Email: bryan@kempville.com
- Documentation: power-switch-pro.readthedocs.io
Test change
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.