Weather MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Weather MCP Server what's the forecast for Austin, Texas?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
# Weather MCP Server
An MCP (Model Context Protocol) server that exposes weather tools — `get_forecast` and `get_alerts` — backed by the US National Weather Service API.
## Setup
uv sync
## Usage
Run standalone to verify it starts correctly:
uv run weather.py
Or connect to it from an MCP client, e.g. the companion [mcp-client](https://github.com/00aimlds00/mcp-client):
uv run client.py path/to/weather.py
## Tools
- **get_forecast(latitude, longitude)** — returns the weather forecast for a US location
- **get_alerts(state)** — returns active weather alerts for a US state (two-letter code)
## Note
Data is sourced from the US National Weather Service, so coverage is limited to US locations.
## Requirements
- Python (see `.python-version`)
## License
MITAvailable Tools
2 toolsget_alertsA
Get weather alerts for a US state.
Args: state: Two-letter US state code (e.g. CA, NY)
Inputs: state (required). Returns: result
get_forecastC
Get weather forecast for a location.
Args: latitude: Latitude of the location longitude: Longitude of the location
Inputs: latitude (required), longitude (required). Returns: result
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 2 tools
get_alerts and get_forecast have entirely distinct purposes: one retrieves weather alerts for a state, the other retrieves forecasts for coordinates. There is no overlap or potential confusion between them.
Both tools follow the same get_noun pattern, making the naming scheme predictable and internally consistent. Even with just two tools, the convention is clear.
Two tools falls into the borderline range for a weather service. While the tools are both useful, the count feels thin for a general-purpose weather server that would typically also include current conditions or location-based search.
The server covers alerts and forecasts, but lacks other common weather operations such as current conditions, hourly forecasts, or marine weather. These are notable gaps, though the two existing tools cover important requested functionality.
Related MCP Connectors
Get US weather forecasts, active and recent alerts, and current observations.
US NWS weather alerts and 5-day forecasts for AI agents. $0.01 per call.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
Related MCP Servers
- AlicenseBqualityDmaintenanceEnables AI assistants to access real-time US weather forecasts and alerts through the National Weather Service API.213 npmMIT
- AlicenseNot gradedqualityDmaintenanceEnables fetching weather alerts for US states and detailed 7-day forecasts for any US location via the National Weather Service API.79 npmGPL 3.0
- FlicenseNot gradedqualityDmaintenanceExposes tools for retrieving weather forecasts and alerts using the National Weather Service API.-
- FlicenseBqualityCmaintenanceProvides an LLM with tools to retrieve US National Weather Service forecasts and active alerts, enabling natural-language answers about current conditions.2-