Supports direct integration with LangChain through langchain-groq, enabling programmatic consumption of weather data in client applications
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 weather alert for Los Angeles?"
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.
A simple demo of MCP python sdk.
start a new project
uv init <project-name>create a virtual environment
uv venvactivate the virtual environment
uv venv --activateinstall the dependencies
uv add <package>
uv add -r requirements.txt
uv syncrun application
uv run app.pyrun the development server
uv run devbuild the project
uv run buildRun server using MCP Inspector :
Install MCP python sdk
uv add "mcp[cli]"Run mcp inspector
uv run mcp dev server/weather.pyMCP Inspector is up and running at http://127.0.0.1:6274
Add server to claude desktop :
run command
uv run mcp install .\server\weather.pyquery "what is weather alert in CA" in claude desktop
Add server to cursor :
goto preferences > settings > mcp and copy paste claude config
{
"mcpServers": {
"weather": {
"command": "uv",
"args": [
"run",
"--with",
"mcp[cli]",
"mcp",
"run",
"C:\\Users\\Suraj\\Desktop\\Python\\mcp-crash-course\\mcpcrashcourse\\server\\weather.py"
]
}
}
}Then do a query in cursor chat
Directly consume server in code - using mcp-use :
Install mcp-use
uv add mcp-useInstall langchain-groq
uv add langchain-groqrun client
uv run server/client.pyGet weather alerts for US state Args: state: Two letter US state code (e.g CA, NY etc)
Inputs: state (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 1 tool
With only one tool, there is no possibility of confusion or overlap between tools. The tool's purpose is clearly defined and distinct by default.
A single tool inherently follows a consistent naming pattern. The tool name 'get_alerts' uses a clear verb_noun format, which would be consistent if more tools were added.
A single tool is too few for a weather server, as it lacks basic operations like getting current conditions, forecasts, or historical data. This severely limits the server's utility and scope.
The tool set is severely incomplete for a weather domain. It only provides alerts for US states, missing essential functions such as retrieving current weather, forecasts, or data for locations outside the US, making it inadequate for typical weather-related tasks.
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
An MCP server for weather information by @kulybaba
An MCP server for weather information by @kulybaba
