The full upstream README, mirrored here for reference. Install config, tool schemas, adoption signals, and an original overview live on the Jettyd MCP listing page.
MCP server for jettyd — gives AI agents direct access to IoT devices.
Connect Claude Desktop, Cursor, Continue, or any MCP-compatible client to your ESP32 devices.
Or globally:
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
Add to your MCP config:
| Tool | Description |
|---|---|
list_devices | List all devices with status |
read_device | Get current sensor readings |
send_command | Send command to device (relay, LED, etc.) |
get_telemetry | Historical sensor readings |
push_rules | Push JettyScript automation rules |
"What's the temperature in the greenhouse?" → Calls
read_device, reads shadow, returns current temperature
"Turn on the irrigation relay for 30 seconds" → Calls
send_commandwithrelay.onand{duration: 30000}
"Alert me if temperature goes above 30°C" → Calls
push_ruleswith a threshold rule
"Show me the humidity trend for the last 24 hours" → Calls
get_telemetrywith metric=air.humidity, period=24h
Sign up at jettyd.com and get your API key from the dashboard.
New to jettyd? The OpenClaw Blueprint walks through the complete setup in 6 steps — hardware, platform, OpenClaw connection, sensors, automations, and dashboard.
github.com/jettydiot/jettyd-mcp
MIT licence