mcp-server-tempest 0.9.0

MCP Server for Retrieving Tempest Weather Data

WeatherFlow Tempest MCP Server

A Model Context Protocol (MCP) server that provides seamless access to WeatherFlow Tempest weather station data. This server enables AI assistants and applications to retrieve real-time weather observations, forecasts, and station metadata.

🌤️ Features

• Real-time Weather Data: Access current conditions from personal weather stations
• Weather Forecasts: Get hourly and daily forecasts with professional meteorological models
• Station Management: Discover and manage multiple weather stations
• Device Information: Detailed metadata about connected weather devices
• Intelligent Caching: Automatic caching with configurable TTL for optimal performance
• Tools for interactive queries and structured weather data
• Comprehensive Data: Temperature, humidity, pressure, wind, precipitation, solar radiation, UV index, and lightning detection

🚀 Quick Start

Prerequisites

• Python 3.13 or higher
• WeatherFlow API token (get one at tempestwx.com/settings/tokens)

Installation

While each client has its own way of specifying, you'll generally use the following values:

Field	Value
Command	uvx
Arguments	mcp-server-tempest
Environment	WEATHERFLOW_API_TOKEN = <YOUR TOKEN>

Development Version

If you'd like to use the latest and greatest, the server can be pulled straight from GitHub. Just add an additional --from argument:

Field	Value
Command	uvx
Arguments	--from, git+https://github.com/briandconnelly/mcp-server-tempest, mcp-server-tempest
Environment	WEATHERFLOW_API_TOKEN = <YOUR TOKEN>

Install as a Desktop Extension (.mcpb)

For one-click installation in apps that support MCP Bundles (e.g. Claude for macOS/Windows):

1. Download the .mcpb from the latest release.
2. Open the file with your MCPB-capable client to launch the install dialog.
3. Paste your WeatherFlow API token when prompted (the cache settings are optional).
4. Make sure the extension is enabled (in Claude Desktop: Settings → Extensions). It is not turned on automatically until the required API token has been provided.

The bundle uses the MCPB uv runtime (manifest_version 0.4), so the host must ship a recent enough uv/MCPB runtime; it resolves dependencies on first launch — no separate Python install is required.

Troubleshooting: if the server fails to start because its install directory is read-only (uv cannot create a .venv next to the bundle), set the UV_PROJECT_ENVIRONMENT environment variable for the server to a writable path before launching.

📋 Configuration

Environment Variables

Variable	Description	Default	Required
WEATHERFLOW_API_TOKEN	Your WeatherFlow API token	-	✅ Yes
WEATHERFLOW_CACHE_TTL	In-memory cache TTL in seconds	300	No
WEATHERFLOW_CACHE_SIZE	Maximum in-memory cache entries	100	No
WEATHERFLOW_DISK_CACHE_TTL	Disk cache TTL in seconds	86400	No

Caching & data freshness

The server caches responses in two layers:

• In-memory (WEATHERFLOW_CACHE_TTL / WEATHERFLOW_CACHE_SIZE): all four tools.
• On disk (WEATHERFLOW_DISK_CACHE_TTL, default 24h): tempest_get_stations and tempest_get_station_details only. Stored under platformdirs.user_cache_dir("mcp-server-tempest") in a per-token (hash-keyed) subdirectory.

To clear: restart the server (in-memory) or delete the cache directory (disk).

Transport

stdio (the default for uvx mcp-server-tempest and the README config).

🛠️ Usage

Available Tools

tempest_get_stations()

Get a list of all your weather stations and connected devices.

# Get all available stations
stations = await client.call_tool("tempest_get_stations")
for station in stations["stations"]:
    print(f"Station: {station['name']} (ID: {station['station_id']})")
    print(f"Location: {station['latitude']}, {station['longitude']}")

tempest_get_observation(station_id)

Get current weather conditions for a specific station.

# Get current conditions
obs = await client.call_tool("tempest_get_observation", {"station_id": 12345})
current = obs["obs"][0]
print(f"Temperature: {current['air_temperature']}°")
print(f"Humidity: {current['relative_humidity']}%")
print(f"Wind: {current['wind_avg']} {obs['station_units']['units_wind']}")

tempest_get_forecast(station_id)

Get weather forecast and current conditions.

# Get forecast
forecast = await client.call_tool("tempest_get_forecast", {"station_id": 12345})

# Current conditions
current = forecast["current_conditions"]
print(f"Current: {current['air_temperature']}°")
print(f"Conditions: {current['conditions']}")

# Today's forecast
today = forecast["forecast"]["daily"][0]
print(f"High/Low: {today['air_temp_high']}°/{today['air_temp_low']}°")
print(f"Rain chance: {today['precip_probability']}%")

tempest_get_station_details(station_id)

Get detailed information about a specific station.

# Get station details
station = await client.call_tool("tempest_get_station_details", {"station_id": 12345})
print(f"Station: {station['name']}")
print(f"Elevation: {station['station_meta']['elevation']}m")
print(f"Devices: {len(station['devices'])}")

🌟 Examples

Basic Weather Check

# Get your stations
stations = await client.call_tool("tempest_get_stations")
station_id = stations["stations"][0]["station_id"]

# Get current conditions
obs = await client.call_tool("tempest_get_observation", {"station_id": station_id})
current = obs["obs"][0]
units = obs["station_units"]

print(f"🌡️  Temperature: {current['air_temperature']}°{units['units_temp']}")
print(f"💧 Humidity: {current['relative_humidity']}%")
print(f"💨 Wind: {current['wind_avg']} {units['units_wind']}")
print(f"🌧️  Precipitation: {current['precip_accum_local_day']} {units['units_precip']}")

Weather Forecast

from datetime import datetime

# Get forecast
forecast = await client.call_tool("tempest_get_forecast", {"station_id": station_id})

# Today's weather
today = forecast["forecast"]["daily"][0]
print(f"📅 Today: {today['conditions']}")
print(f"🌡️  High: {today['air_temp_high']}° / Low: {today['air_temp_low']}°")
print(f"🌧️  Rain chance: {today['precip_probability']}%")

# Next few hours
for hour in forecast["forecast"]["hourly"][:6]:
    time = datetime.fromtimestamp(hour["time"])
    print(f"🕐 {time.strftime('%H:%M')}: {hour['air_temperature']}° - {hour['conditions']}")

Station Information

# Get station details
station = await client.call_tool("tempest_get_station_details", {"station_id": station_id})

print(f"🏠 Station: {station['name']}")
print(f"📍 Location: {station['latitude']}°, {station['longitude']}°")
print(f"⛰️  Elevation: {station['station_meta']['elevation']}m")
print(f"🕐 Timezone: {station['timezone']}")

# Check device status
for device in station["devices"]:
    if device.get("serial_number"):
        status = "🟢 Online" if device.get("device_meta") else "🔴 Offline"
        print(f"📡 {device['device_type']}: {status}")

🤝 Contributing

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• WeatherFlow for providing the Tempest weather station and API
• Model Context Protocol for the MCP specification
• FastMCP for the MCP server framework

📞 Support

• Issues: GitHub Issues
• Documentation: WeatherFlow API Docs
• Community: WeatherFlow Community