Skip to content
Conduit

mcp server

epwtools-python

Python client, CLI and MCP server for EPW.tools: EnergyPlus weather files (EPW, DDY, STAT) for any location, past years, typical years and future climate

carlobianchi89/epwtools-pythoncommunitylistedunreviewed
Use tool

Set up

Runs on your computer. Pick your agent and operating system.

Before you start

  • uv (`curl -LsSf https://astral.sh/uv/install.sh | sh`)
~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "epwtools-python": {
      "command": "uvx",
      "args": [
        "epwtools"
      ],
      "env": {
        "EPWTOOLS_API_KEY": "<your EPWTOOLS_API_KEY>"
      }
    }
  }
}

same format Cursor, GitHub Copilot CLI, Junie, JetBrains AI Assistant, Augment (Auggie CLI), Factory Droid, Kiro, Devin CLI +12

Values in angle brackets are placeholders. Restart Claude Desktop after editing its config.Claude Desktop docs

README

synced Nov 8, 2026

epwtools

carlobianchi89/epwtools-python MCP server epwtools on AI Agents Listing M8ven Score

Python client, command-line tool and MCP server for EPW.tools: EnergyPlus weather files (EPW, with DDY design days and STAT summaries) for any location on Earth.

  • Actual years from 1990 to now, for any coordinates, with or without a nearby weather station
  • Typical years (TMY), extreme and heatwave years
  • Future climate for 2030 to 2100 under SSP scenarios
  • Design conditions (ASHRAE method) and short-term forecast weather files

The weather data are built and validated by EPW.tools (methodology, validation); this package is the open-source way to call them from Python, the terminal or an AI assistant.

Install

pip install epwtools            # client + CLI
pip install 'epwtools[mcp]'     # + MCP server for AI assistants

Get a free API key at epw.tools (API tab); the first files are free.

export EPWTOOLS_API_KEY=your-key

Python

from epwtools import EPWClient

client = EPWClient()                       # reads EPWTOOLS_API_KEY

# actual year 2023 for a site in Denver
epw = client.generate(lat=39.74, lon=-104.99, year=2023, name="Denver", out_dir="weather")

# typical year built from 2005-2024
tmy = client.tmy(lat=45.46, lon=9.19, start=2005, end=2024, name="Milan", out_dir="weather")

# design conditions (ASHRAE method)
dc = client.design_conditions(lat=51.51, lon=-0.13)

Command line

epwtools configure                          # store your key
epwtools generate --lat 39.74 --lon -104.99 --year 2023 --name Denver
epwtools tmy --lat 45.46 --lon 9.19 --start 2005 --end 2024 --name Milan
epwtools future --lat 40.71 --lon -74.01 --scenario ssp245 --horizon 2050 --name NYC
epwtools --help

AI assistants (MCP)

Let Claude, ChatGPT and other MCP-capable assistants make weather files for you:

uvx --from 'epwtools[mcp]' epw-tools-mcp

or use the hosted server, listed in the official MCP Registry. Tools include generate_epw, generate_tmy, generate_future_climate, generate_forecast, get_design_conditions and get_nearest_stations. Setup guide: epw.tools/ai-weather-files.

Also on EPW.tools (web)

EPW to CSV / Excel converter · Manual J design temperatures by address · Construction weather days · Data-centre site climate · API licence for software vendors

Licence

The client, CLI and MCP server in this repository are MIT-licensed. Use of the EPW.tools service and its data is governed by the EPW.tools terms of service (linked in the footer of epw.tools).

↑↓ navigate openesc close