Built using Node.js to implement MCP tools for weather data retrieval from the US National Weather Service API.
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., "@MCP Weather Server get weather alerts for California"
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.
This project is a demo implementation of a Model Context Protocol (MCP) server that provides weather-related tools. The server exposes two tools:
get-alerts: Fetches active weather alerts for a given US state.
get-forecast: Provides a weather forecast for a specific location based on latitude and longitude.
Built using Node.js.
Implements MCP tools for weather data retrieval.
Uses the US National Weather Service API for accurate and up-to-date weather information.
Related MCP server: Weather MCP Server
Node.js installed on your system.
Familiarity with MCP concepts and tools.
To install mcp-server-learn for Claude Desktop automatically via Smithery:
npx -y @smithery/cli install @adarshem/mcp-server-learn --client claudeClone the repository:
git clone <repository-url>
cd weatherInstall dependencies using pnpm (as configured in the project):
pnpm installBuild the project:
pnpm buildUpdate your settings.json file of VSCode to add this MCP server
{
"mcpServers": {
"weather": {
"command": "node",
"args": [
"/ABSOLUTE/PATH/TO/PARENT/FOLDER/weather/build/index.js"
]
}
}
}Get weather alerts for a state
Inputs: state (required).
Get weather forecast for a location
Inputs: latitude (required), longitude (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have clearly distinct purposes: get-alerts focuses on weather alerts for a state, while get-forecast provides weather forecasts for a location. There is no overlap in functionality, making it easy for an agent to choose the correct tool based on the need for alerts versus forecasts.
Both tool names follow a consistent verb_noun pattern with hyphens (get-alerts and get-forecast). This uniformity makes the tool set predictable and easy to understand, with no deviations in naming conventions.
With only two tools, the server feels thin for a weather domain, as it lacks essential operations like current conditions, historical data, or radar information. While the tools are well-defined, the count is too low to provide comprehensive coverage for typical weather-related tasks.
The tool set is severely incomplete for a weather server, missing core functionalities such as current weather conditions, historical data, radar maps, and air quality information. This limited surface will likely cause agent failures when users request common weather data beyond alerts and forecasts.
Hosted MCP server for Xweather weather data: conditions, forecasts, alerts, and more.
The official Model Context Protocol server for Ambee. It gives any MCP-compatible AI assistant — Claude, ChatGPT, Cursor, VS Code, Ollama, and more direct access to live air quality, pollen, and weather data. To get started, including information on signing up and obtaining your Ambee key, check out the Ambee documentation on https://docs.ambeedata.com
MCP server for weather with reasoning — umbrella advice, outdoor checks, city comparisons.
NOAA and ECMWF weather forecast MCP for discovery, validation, and GribStream OAuth queries.
