Click on "Install 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 in Tokyo?"
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 Model Context Protocol (MCP) server that provides weather forecasts and geocoding lookup using the free, keyless Open-Meteo APIs. This server enables LLMs (like Claude, Gemini, and GPT) to query real-time weather information and multi-day forecasts for any city or location in the world.
Get Current Weather: Detailed current conditions including condition description, temperature, apparent temperature (feels like), humidity, wind speed, and precipitation details.
Multi-day Weather Forecast: Standard 1-7 day forecast with conditions, daily min/max temperatures, and total expected precipitation.
Keyless & Free: Powered by the open-source Open-Meteo APIs, requiring no API keys or subscription signups.
Fuzzy Geocoding: Automatically resolves location names (e.g., "Paris", "New York", "London") to geographic coordinates and timezones.
Related MCP server: open-meteo-mcp-server
You can run this server directly from npm using npx, or install it globally.
npx (Recommended)To run the server without installation:
npx -y weather-mcp-serverInstall the package globally:
npm install -g weather-mcp-serverThen run it:
weather-mcp-serverTo add the Weather MCP Server to Claude Desktop, edit your claude_desktop_config.json file.
Windows path: %APPDATA%\Claude\claude_desktop_config.json
macOS path: ~/Library/Application Support/Claude/claude_desktop_config.json
Add the server to the mcpServers list:
{
"mcpServers": {
"weather": {
"command": "npx",
"args": [
"-y",
"weather-mcp-server"
]
}
}
}Cursor supports custom MCP servers directly from the GUI:
Open Cursor Settings (Ctrl + , or Cmd + ,).
Go to Features -> MCP.
Click + Add New MCP Server.
Fill in:
Name: Weather
Type: command
Command: npx -y weather-mcp-server
Click Save.
This server exposes a single tool called get_weather.
get_weatherGets the current weather and daily forecast for a given location.
Arguments:
location (string, required): The city, region, or location name (e.g. "Tokyo", "Paris", "Chicago, IL").
days (number, optional, default: 3): Number of forecast days to return (integer between 1 and 7).
Example Request:
{
"name": "get_weather",
"arguments": {
"location": "Paris",
"days": 3
}
}If you want to run the server locally from the source code, follow these steps:
Clone or download the repository.
Install dependencies:
npm installBuild the TypeScript code:
npm run buildRun locally:
npm startTo link and test the local version in Claude Desktop, point the configuration directly to the local path:
{
"mcpServers": {
"weather-local": {
"command": "node",
"args": [
"C:/path/to/your/project/dist/index.js"
]
}
}
}ISC License. Feel free to use and adapt this server.
Get the current weather and 1-7 day forecast for a specific location.
| Name | Required | Description | Default |
|---|---|---|---|
| days | No | Number of forecast days (1-7, default is 3) | |
| location | Yes | The name of the city, region, or location (e.g. 'New York', 'Tokyo') |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It reveals the core behavior (current weather and forecast range) but omits details such as response format, error handling, or data source. This partial disclosure is adequate but not fully transparent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single, focused sentence that immediately communicates the tool's purpose. It is concise, front-loaded, and contains no unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with a well-documented schema, the description covers the essential function and scope. However, the absence of an output schema and lack of mention of return values or edge cases leave minor gaps, though they are not critical for a basic weather lookup.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema provides complete descriptions for both parameters, including examples and default values. The tool description adds no new semantic information beyond what the schema already covers, so the baseline score of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool retrieves current weather and a 1-7 day forecast for a specific location, using a clear verb ('get') and a specific resource ('weather'). It unambiguously defines what the tool does without ambiguity.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There are no sibling tools or explicit alternative mentioned, and the description does not state when to use this tool versus others. It implies usage for weather requests but provides no exclusions or prerequisites, leaving the guidance implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
With only one tool, there is no possibility of confusion or overlap. Every tool (the only tool) has a clearly distinct purpose.
The single tool name 'get_weather' follows a consistent verb_noun pattern, which is a standard and clear convention. There are no other tools to create inconsistency.
The server has exactly one tool, which feels too thin for the apparent scope of a weather service. While the tool covers current and forecast data, a typical weather server might offer additional operations like alerts or historical data.
The single tool covers the core weather use case of current conditions and 1-7 day forecast. Minor gaps exist—such as weather alerts, historical data, or multi-location retrieval—but they are not essential to the primary purpose.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Global weather via Open-Meteo: forecast, ERA5 archive, marine, air quality, geocoding, elevation.
Real-time weather conditions and multi-day forecasts via Open-Meteo — free, no API key required
US weather & geo for AI agents: forecasts, alerts, earthquakes, elevation, geocoding. No keys.
Geocoding, weather forecasts, and timezone lookups
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/itachiuchihadev/weather_mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server