uecs-ccm-mcp
Enables reading of greenhouse sensor data and sending actuator commands directly over UECS-CCM UDP multicast, with no MQTT broker needed.
README
uecs-ccm-mcp
MCP server for UECS-CCM greenhouse monitoring and control.
Directly participates in UECS (Ubiquitous Environment Control System) CCM multicast network to read sensor data and send actuator commands — no MQTT broker required.
What is UECS-CCM?
UECS is the Japanese standard protocol for greenhouse environment control, using UDP multicast (224.0.0.1:16520) with XML payloads. CCM (Communication Control Module) packets carry sensor readings (temperature, humidity, CO2, etc.) and actuator commands (irrigation, ventilation, curtain, etc.).
Features
- 5 MCP tools for LLM-driven greenhouse control
- Zero-config networking: joins UDP multicast automatically
- Safety guardrails: actuator allowlist, rate limiting, max irrigation duration
- No MQTT dependency: talks CCM directly
- Standalone test scripts: scp to RPi and run with zero dependencies
Quick Start
Install
pip install uecs-ccm-mcp
Run as MCP Server
uecs-ccm-mcp
Claude Desktop / Claude Code
Add to your MCP config:
{
"mcpServers": {
"greenhouse": {
"command": "uecs-ccm-mcp"
}
}
}
MCP Tools
| Tool | Description |
|---|---|
get_sensor_data |
Indoor sensors (temp, humidity, CO2, soil temp, etc.) |
get_actuator_status |
Actuator states (irrigation, ventilation, curtain) |
set_actuator |
Control actuators with safety guardrails |
get_weather_summary |
Outdoor weather station data |
list_nodes |
Active UECS nodes on the network |
Field Test Scripts
Standalone scripts (Python standard library only) for testing on RPi:
# Receive CCM packets
python3 scripts/ccm_receive_test.py
python3 scripts/ccm_receive_test.py --filter InAirTemp
# Send control packets (confirm before sending)
python3 scripts/ccm_send_test.py Irri 1 # Irrigation ON
python3 scripts/ccm_send_test.py Irri 0 # Irrigation OFF
python3 scripts/ccm_send_test.py VenRfWin 50 # Roof window 50%
Supported Hardware
Tested with:
- ArSprout greenhouse controller (sensor/actuator nodes)
- Raspberry Pi as CCM participant
- Any UECS-compliant node
Safety
- Only allowlisted actuator types can be controlled
- Minimum 1 second between commands (rate limiting)
- Maximum 3600 second irrigation duration
- Auto-OFF timer support
License
MIT
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.