This server provides real-time weather information for any city using the OpenWeather API.
Fetches current weather by city name (e.g., London, Chennai, New York)
Returns temperature (°C), feels-like temperature, humidity, pressure, weather condition, description, and wind speed (m/s)
Output is structured JSON with city and country information
Uses an OpenAI API key from environment variables for authentication
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 in London?"
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 built with Python and uv that provides weather information by city name using the OpenWeather API (https://api.openweathermap.org/data/2.5/weather).
Related MCP server: Weather MCP Server
Get Weather by City Name: Fetches real-time weather metrics for any city (e.g., London, Chennai, New York,US).
Structured JSON Output: Returns temperature (°C), feels-like (°C), humidity (%), pressure (hPa), weather conditions, and wind speed (m/s).
Environment Key Integration: Loads OPENWEATHER_API_KEY automatically via .env / dotenv.
Package Management via uv: Uses pyproject.toml and uv for reproducible builds.
Python: >= 3.10
uv: Fast Python package manager (Installation Guide)
Node.js & npx (Optional, for testing with MCP Inspector)
OpenWeather API Key: Free key from OpenWeather SignUp
cd /Users/jayarajkannan/Learnings/project/mcpCreate a .env file from .env.example and set your OpenWeather API key:
cp .env.example .envEdit .env:
OPENWEATHER_API_KEY=your_actual_openweather_api_key_hereSync virtual environment and lockfile using uv:
uv syncThis installs mcp, httpx, and python-dotenv into the project environment.
You can run the server directly using uv:
uv run server.pyOr using the CLI script entry point defined in pyproject.toml:
uv run weather-mcpNote: MCP servers communicate over
stdiovia JSON-RPC. Running the script directly will wait for input on stdin.
Use the official MCP Inspector to test and verify all tool calls in your browser UI:
npx @modelcontextprotocol/inspector uv run server.pyOpen the URL printed in the terminal (e.g. http://127.0.0.1:6274?...).
Click Connect.
Select the get_weather tool.
Input a city name (e.g. London or Chennai) and click Run Tool.
Run the test suite using unittest and uv:
uv run python -m unittest test_server.pyget_weatherGets current weather for a city using OpenWeather API.
Parameter | Type | Required | Description |
|
| Yes | City name (e.g. |
{
"city": "London",
"country": "GB",
"temperature_c": 21.57,
"feels_like_c": 21.58,
"humidity": 69,
"pressure": 1006,
"weather": "Clouds",
"description": "broken clouds",
"wind_speed_mps": 9.26
}Add the Weather MCP server to your MCP client configuration (e.g. Claude Desktop claude_desktop_config.json or Antigravity .mcp.json):
ctrl+shift+p for windows , cmd+shift+p mac
search >mcp: open user configuration
it will open a mcp.json file update the below config there
{
"mcpServers": {
"weather": {
"command": "uv",
"args": [
"--directory",
"/Users/jayarajkannan/Learnings/project/mcp",
"run",
"server.py"
],
"env": {
"OPENWEATHER_API_KEY": "YOUR_OPENWEATHER_API_KEY"
}
}
}
}├── pyproject.toml # Project dependencies and script entry points
├── uv.lock # Locked dependency tree
├── server.py # Weather MCP server implementation
├── test_server.py # Automated unit tests
├── .env.example # Sample environment configuration
├── .env # Local environment variables (API Key)
└── README.md # DocumentationGet current weather for a city.
Args: city: City name (e.g. London, Chennai, New York)
Returns: Weather details including temperature, humidity, and conditions.
| Name | Required | Description | Default |
|---|---|---|---|
| city | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the behavioral burden. It does disclose that the result includes temperature, humidity, and conditions, but it does not mention units, city-resolution behavior, possible errors, or whether the operation is strictly read-only. This is acceptable but minimal.
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 compact and well-structured: one clear purpose sentence, an Args block, and a Returns block. Every sentence earns its place and the main purpose is front-loaded.
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 one-parameter tool with an output schema available, this description is sufficient for an agent to select and invoke the tool correctly. It could add minor caveats like units or error behavior, but those are not necessary for basic correct use.
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 JSON schema provides only the parameter title 'City' with 0% description coverage, so the description's Args section adds crucial meaning by explaining that it expects a city name and giving concrete examples. It could add disambiguation guidance for duplicate city names, but for a single required parameter it compensates well.
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 opening sentence 'Get current weather for a city' uses a specific verb and resource and immediately communicates the tool's purpose. It also clearly identifies the input (a city) and expected output, making the tool easy to distinguish even without siblings.
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?
The phrase 'current weather' makes the intended use case clear: this tool is for real-time conditions, not forecasts or historical data. There are no sibling tools and no exclusions to document, so the usage context is sufficiently clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0get_weatherScored across 1 tool
With only one tool, there is no possibility of confusing it with others. The tool's purpose is clearly stated and unambiguous.
The single tool name follows a clear verb_noun pattern. However, with only one example, consistency cannot be fully assessed.
A single tool is too few for a weather-focused server, which would typically also cover forecasts, historical data, or location-based queries. The tool provides only current conditions.
The tool surface is severely limited to current weather only. Obvious gaps include forecasts, severe weather alerts, historical weather, and geocoding or location disambiguation.
Free, keyless real-time weather and 7-day forecasts for any city worldwide.
Provide real-time and forecast weather information for locations in the United States using natura…
Get current weather for any city and create images from your prompts. Streamline planning, reports…
Global weather via Open-Meteo: forecast, historical, marine, air quality, geocoding, elevation.