The MCP Weather Server is a Model Context Protocol (MCP) server that provides weather and time-related information through the Open-Meteo API. It supports both standard MCP communication for AI clients and HTTP Server-Sent Events (SSE) for web applications.
Install the package using pip:
pip install mcp_weather_server
Add the following entry to the mcpServers
object in your cline_mcp_settings.json
file:
{
"mcpServers": {
"weather": {
"command": "python",
"args": [
"-m",
"mcp_weather_server"
],
"disabled": false,
"autoApprove": []
}
}
}
For HTTP SSE support, install additional dependencies:
pip install mcp_weather_server starlette uvicorn
# Default mode (stdio)
python -m mcp_weather_server
# Explicitly specify stdio mode
python -m mcp_weather_server.server --mode stdio
# Start SSE server on default host/port (0.0.0.0:8080)
python -m mcp_weather_server.server --mode sse
# Specify custom host and port
python -m mcp_weather_server.server --mode sse --host localhost --port 3000
# Enable debug mode
python -m mcp_weather_server.server --mode sse --debug
--mode {stdio,sse} Server mode: stdio (default) or sse
--host HOST Host to bind to (SSE mode only, default: 0.0.0.0)
--port PORT Port to listen on (SSE mode only, default: 8080)
--debug Enable debug mode
The server provides several weather and time-related tools:
Retrieves the current weather information for a given city.
Parameters:
city
(string, required): The name of the city (English names only)Example:
<use_mcp_tool>
<server_name>weather</server_name>
<tool_name>get_current_weather</tool_name>
<arguments>
{
"city": "Tokyo"
}
</arguments>
</use_mcp_tool>
Returns:
{
"city": "Taipei",
"weather": "Partly cloudy",
"temperature_celsius": 25
}
Retrieves weather information for a specified city between start and end dates.
Parameters:
city
(string, required): The name of the city (English names only)start_date
(string, required): Start date in format YYYY-MM-DDend_date
(string, required): End date in format YYYY-MM-DDExample:
<use_mcp_tool>
<server_name>weather</server_name>
<tool_name>get_weather_by_datetime_range</tool_name>
<arguments>
{
"city": "Paris",
"start_date": "2024-01-01",
"end_date": "2024-01-07"
}
</arguments>
</use_mcp_tool>
Returns:
[
{
"date": "2024-01-01",
"day_of_week": "Monday",
"city": "London",
"weather": "Light rain",
"temperature_celsius": 8
}
]
Retrieves the current time in a specified timezone.
Parameters:
timezone_name
(string, required): IANA timezone name (e.g., 'America/New_York')Example:
<use_mcp_tool>
<server_name>weather</server_name>
<tool_name>get_current_datetime</tool_name>
<arguments>
{
"timezone_name": "Europe/Paris"
}
</arguments>
</use_mcp_tool>
Returns:
{
"timezone": "America/New_York",
"current_time": "2024-01-15T14:30:00-05:00",
"utc_time": "2024-01-15T19:30:00Z"
}
Get information about a specific timezone.
Parameters:
timezone_name
(string, required): IANA timezone nameConvert time from one timezone to another.
Parameters:
time_str
(string, required): Time to convert (ISO format)from_timezone
(string, required): Source timezoneto_timezone
(string, required): Target timezoneWhen running in SSE mode, you can integrate with web applications:
<!DOCTYPE html>
<html>
<head>
<title>Weather MCP Client</title>
</head>
<body>
<div id="weather-data"></div>
<script>
// Connect to SSE endpoint
const eventSource = new EventSource('http://localhost:8080/sse');
eventSource.onmessage = function(event) {
const data = JSON.parse(event.data);
document.getElementById('weather-data').innerHTML = JSON.stringify(data, null, 2);
};
// Function to get weather
async function getWeather(city) {
const response = await fetch('http://localhost:8080/messages/', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
jsonrpc: '2.0',
method: 'tools/call',
params: {
name: 'get_current_weather',
arguments: { city: city }
},
id: 1
})
});
}
// Example: Get weather for Tokyo
getWeather('Tokyo');
</script>
</body>
</html>
City not found
SSE Server not accessible
MCP Client connection issues
mcp_weather_server
package is installedDate format errors
To add this MCP server to Claude Code, run this command in your terminal:
claude mcp add-json "weather" '{"command":"python","args":["-m","mcp_weather_server"],"disabled":false,"autoApprove":[]}'
See the official Claude Code MCP documentation for more details.
There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json
file so that it is available in all of your projects.
If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json
file.
To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".
When you click that button the ~/.cursor/mcp.json
file will be opened and you can add your server like this:
{
"mcpServers": {
"weather": {
"command": "python",
"args": [
"-m",
"mcp_weather_server"
],
"disabled": false,
"autoApprove": []
}
}
}
To add an MCP server to a project you can create a new .cursor/mcp.json
file or add it to the existing one. This will look exactly the same as the global MCP server example above.
Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.
The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.
You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.
To add this MCP server to Claude Desktop:
1. Find your configuration file:
~/Library/Application Support/Claude/claude_desktop_config.json
%APPDATA%\Claude\claude_desktop_config.json
~/.config/Claude/claude_desktop_config.json
2. Add this to your configuration file:
{
"mcpServers": {
"weather": {
"command": "python",
"args": [
"-m",
"mcp_weather_server"
],
"disabled": false,
"autoApprove": []
}
}
}
3. Restart Claude Desktop for the changes to take effect