Measure Space MCP Server

What is Measure Space MCP Server about?

The server delivers hourly and daily weather forecasts, multi‑month climate outlooks, short‑term air‑quality predictions, and geocoding services (city‑to‑coordinates and reverse). It is built with FastAPI and follows the Model Context Protocol, enabling AI assistants to fetch environmental data programmatically.

How to use Measure Space MCP Server?

1. Installation via Smithery (recommended)

   npx -y @smithery/cli install @MeasureSpace/measure-space-mcp-server --client claude
   

2. Manual installation

   git clone git@github.com:MeasureSpace/measure-space-mcp-server.git
   cd measure-space-mcp-server
   uv venv
   uv pip install -e .
   

   Create a .env file with the required API keys (geocoding, weather, climate, air‑quality).
3. Running the server

   python main.py
   

   The service listens on http://localhost:8000 by default.
4. Configure Claude Desktop (or any MCP‑compatible client) by adding the server entry to cladue_desktop_config.json as described in the README.

Key Features of Measure Space MCP Server

• Hourly weather forecast for the next 5 days
• Daily weather forecast for the next 15 days
• Daily climate forecast for up to 9 months
• Hourly & daily air‑quality forecast for the next 4 days
• Forward geocoding (city name → latitude/longitude)
• Reverse geocoding (coordinates → nearest city)
• Timezone lookup
• Astronomy data (sunrise, sunset times)
• FastAPI‑based, easy to extend with additional endpoints

Use Cases

• Building AI assistants that can answer location‑specific weather or air‑quality questions.
• Integrating real‑time environmental data into smart‑home or IoT dashboards.
• Providing backend services for mobile or web apps that need forecast or geocoding information.
• Enabling research tools that require bulk access to climate projections.

FAQ

Q: Which Python version is required?
A: Python 3.12 or newer.

Q: Do I need all API keys?
A: No. Provide only the keys for the services you plan to use (e.g., geocoding only requires GEOCODING_API_KEY).

Q: Can I run the server in a Docker container?
A: Yes. Build a Docker image that installs the package and copies your .env file; then run the container exposing port 8000.

Q: How do I update the server?
A: Pull the latest changes from the GitHub repository and reinstall with uv pip install -e . or re‑run the Smithery install command.

MCP Server for Measure Space API Services

A Model Context Protocol (MCP) server for weather, climate, and air quality forecast and geocoding services from measurespace.io, built with FastAPI and the MCP framework. This server provides various weather, climate, air quality and geocoding related tools that can be used by AI assistants to retrieve weather, climate and air quality forecasts and more.

Features

• Hourly weather forecast for next 5 days
• Daily weather forecast for next 15 days
• Daily climate forecast for next 9 months
• Hourly and daily air quality forecast for next 4 days
• Geocoding service for finding latitude and longitude for given city names
• Geocoding service for find nearest city for given latitude and longitude
• Timezone information
• Astronomy data (sunrise, sunset)

Requirements

• Python 3.12+
• uv package manager
• Related service API keys from measurespace.io

Installation

Installing via Smithery

To install this server for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install @MeasureSpace/measure-space-mcp-server --client claude

Manual Installation

1. Clone this repository:

   git clone git@github.com:MeasureSpace/measure-space-mcp-server.git
   cd measure-space-mcp-server
   

2. Install dependencies using uv:

   uv venv
   uv pip install -e .
   

3. Create a .env file in the project root with your related API keys from measurespace.io:

   GEOCODING_API_KEY=<your-geocoding-api-key>
   HOURLY_WEATHER_API_KEY=<your-hourly-weather-api-key>
   DAILY_WEATHER_API_KEY=<your-daily-weather-api-key>
   DAILY_WEATHER_API_KEY=<your-daily-climate-api-key>
   AIR_QUALITY_API_KEY=<your-air-quality-api-key>
   

   Note that you only need the API key for the service your need.

Usage

Use the server with Claude Desktop App

Open the cladue_desktop_config.json file and add the following setup. Restart the Claude Desktop App. Please see this tutorial if you don't know where to find the cladue_desktop_config.json file.

{
  "mcpServers": {
    "MeasureSpace": {
      "command": "/<your_uv_path>/uv",
      "args": [
        "--directory",
        "/<your-measure-space-mcp-server-folder-path>/measure-space-mcp-server",
        "run",
        "main.py"
      ]
    }
  }
}

Run the server

# Go into your uv built environment
python main.py

The server will start on http://localhost:8000 by default.