# EPW.tools (pypi · epwtools)

EnergyPlus weather files (EPW, DDY, STAT) and design conditions for any site, OpenStudio-MCP ready.

- Trust score: 66/100 (medium)
- Change this week: +8
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-18

## Components

- pypi · `epwtools`: 66/100 (this document), [markdown](https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools.md), [page](https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools)

## Channel facts

- Registry: `pypi`
- Package: `epwtools`
- Version: `0.5.1`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-18.

- **Supply Chain Security**: 99/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 3 of 13 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 6/100
  - Repository check failed: no source repository is declared.
  - Build provenance not yet verified.
  - License check failed: the license (Proprietary) isn't a recognized OSI-approved license.
  - Actively maintained (last published 1 days ago).
  - Security-disclosure policy not yet verified: we couldn't inspect the source repository.
- **Schema Quality & AI Usability**: 57/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 2119 tokens (~264/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 63/100
  - Stability observed for 19 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the EPW.tools MCP server?

EPW.tools runs locally as a PyPI package, launched with uvx epwtools. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add carlobianchi89-epwtools -- uvx epwtools
```

### Cursor

```json
{
  "mcpServers": {
    "carlobianchi89-epwtools": {
      "command": "uvx",
      "args": [
        "epwtools"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "carlobianchi89-epwtools": {
      "command": "uvx",
      "args": [
        "epwtools"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add carlobianchi89-epwtools -- uvx epwtools
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "carlobianchi89-epwtools": {
      "type": "local",
      "command": [
        "uvx",
        "epwtools"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add carlobianchi89-epwtools --command uvx --arg epwtools
```

### Hermes

```yaml
mcp_servers:
  carlobianchi89-epwtools:
    command: "uvx"
    args: ["epwtools"]
```

### Netclaw

```json
{
  "McpServers": {
    "carlobianchi89-epwtools": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "epwtools"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add carlobianchi89-epwtools -t stdio -c uvx -a epwtools
```

### Other

```json
{
  "mcpServers": {
    "carlobianchi89-epwtools": {
      "command": "uvx",
      "args": [
        "epwtools"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-18 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 60 to 63. That category is still filling its 30-day observation window: 18 days of observed history at the previous scan, 19 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-17 (score 65, −1)

- [security regression] Malware scan: pass → unverified
- [security regression] Provenance: fail → unverified
- [functional regression] Schema quality: 176 → 264
- [functional regression] Schema quality: 176 → 251
- [functional] Package version: 0.4.0 → 0.5.1
- [functional] Package version: 0.4.0 → 0.5.0

### 2026-10-16 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-14 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-13 (score 64, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-10-12 (score 49, −9)

- [security regression] Malware scan: pass → unverified
- [functional improvement] Stability: unverified → 0.43

### 2026-09-30 (score 58, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-09-29 (score 43)

First indexed and scored.

## MCP tools (8)

### `generate_epw` (~375 tokens)

Generate a single-year AMY EPW file (+ DDY + STAT) for any location worldwide.

Args:
    lat: Latitude in decimal degrees (-90 to 90).
    lon: Longitude in decimal degrees (-180 to 180).
    year: Calendar year, 1990 to last year (complete years only).
    location_name: Name used in output filenames and EPW header.
    data_source: "merra2" (Standard, global, default), "open-meteo" (ERA5 via Open-Meteo, global), "hrrr" (3 km, US only), "satellite" (satellite solar: Europe, Africa, S. America, Asia, Australia) or "cweeds" (Canada station solar).
    dc_edition: ASHRAE design conditions edition: "2025", "2021", "2017", "2013", "2009", or "2005".
    save_to: Optional local folder; the EPW, DDY and STAT are saved there under one base name
             (ready for OpenStudio-MCP's change_building_location).
    leap_day: Leap years only. "remove" (default) drops 29 February (8760 hours; EnergyPlus weekdays from
              1 March then fall one day early). "keep" writes the true calendar (8784 hours).

Returns:
    JSON string with job_id, status, and download links for EPW/DDY/STAT files.

Input parameters:

- `data_source` (string)
- `dc_edition` (string)
- `lat` (number, required)
- `leap_day` (string)
- `location_name` (string)
- `lon` (number, required)
- `save_to`
- `year` (integer, required)

Output parameters:

- `result` (string)

### `generate_forecast` (~260 tokens)

Generate a short-horizon forecast EPW: the next 1–15 days of weather as a
simulation-ready (partial) EPW, for model-predictive control, demand-response
and other operational building-energy simulations.

Unlike the other tools this returns a partial-year EPW covering only the
forecast window; set your EnergyPlus RunPeriod to the dates in the file's
DATA PERIODS header. US locations use a high-resolution model automatically.

Args:
    lat: Latitude in decimal degrees (-90 to 90).
    lon: Longitude in decimal degrees (-180 to 180).
    location_name: Name used in output filenames and EPW header.
    forecast_days: Horizon in days (1–15). Default 7.
    dc_edition: ASHRAE design conditions edition.
    save_to: Optional local folder to save the EPW (and DDY/STAT if produced).

Returns:
    JSON string with job_id, status, and a download link for the forecast EPW.

Input parameters:

- `dc_edition` (string)
- `forecast_days` (integer)
- `lat` (number, required)
- `location_name` (string)
- `lon` (number, required)
- `save_to`

Output parameters:

- `result` (string)

### `generate_tmy` (~279 tokens)

Generate a custom Typical Meteorological Year (TMY) EPW using the
Sandia/Finkelstein-Schafer method over a multi-year MERRA-2 record.

Args:
    lat: Latitude in decimal degrees.
    lon: Longitude in decimal degrees.
    location_name: Name used in output filenames.
    start_year: First year of the averaging period (2000–2024, min span 5 yr).
    end_year: Last year of the averaging period (max span 25 yr).
    dc_edition: ASHRAE design conditions edition.
    weights: Optional dict of variable weights, e.g.:
             {"dbt": 4, "dwpt": 4, "ghi": 12, "wspd": 3}.
             Defaults to Sandia TMY3 standard weights.
    save_to: Optional local folder; EPW, DDY and STAT saved there under one base name.

Returns:
    JSON string with job_id, status, and download link for the TMY EPW.

Input parameters:

- `dc_edition` (string)
- `end_year` (integer)
- `lat` (number, required)
- `location_name` (string)
- `lon` (number, required)
- `save_to`
- `start_year` (integer)
- `weights`

Output parameters:

- `result` (string)

### `generate_future_climate` (~284 tokens)

Generate a future climate EPW using CMIP6 Belcher morphing applied to a
MERRA-2 baseline year.

Args:
    lat: Latitude in decimal degrees.
    lon: Longitude in decimal degrees.
    location_name: Name for output files.
    scenario: SSP scenario — "ssp126", "ssp245", "ssp370", or "ssp585".
    horizon: Future time horizon — 2030, 2050, 2070, or 2100.
    base_year: MERRA-2 baseline year (1985–2014).
    model: CMIP6 GCM name, e.g. "MRI-ESM2-0", "GFDL-ESM4", "IPSL-CM6A-LR".
    dc_edition: ASHRAE design conditions edition.
    save_to: Optional local folder; EPW, DDY and STAT saved there under one base name.

Returns:
    JSON string with job_id, status, and download link.

Input parameters:

- `base_year` (integer)
- `dc_edition` (string)
- `horizon` (integer)
- `lat` (number, required)
- `location_name` (string)
- `lon` (number, required)
- `model` (string)
- `save_to`
- `scenario` (string)

Output parameters:

- `result` (string)

### `get_design_conditions` (~472 tokens)

Heating and cooling design conditions for any location, in one of two modes that are never mixed.
Values are free (no API key). The ASHRAE-method DDY is free; saving the Enhanced DDY costs 1 credit and
needs EPWTOOLS_API_KEY.

mode="ashrae_method": the ASHRAE Handbook (Ch. 14) method replicated by EPW.tools at the nearest ASHRAE
    station over the chosen edition's period (validated ~0.2 C from the published tables). Use where a
    specification or code asks for ASHRAE design conditions.
mode="enhanced": EPW.tools Enhanced, NOT the ASHRAE method: values at the site itself (23-50 % closer
    than the nearest station in a leave-one-station-out test), moved to the coming decade's climate
    (current_climate=True), each with a tested 90 % range, plus design heat waves and cold spells. Use for
    sizing decisions and risk.

Args:
    lat, lon: Site coordinates in decimal degrees.
    mode: "ashrae_method" or "enhanced".
    edition: ASHRAE edition for mode="ashrae_method": 2025, 2021, 2017, 2013, 2009, 2005.
    current_climate: Enhanced only; False keeps the 1999-2023 climate.
    location_name: Name written into the DDY.
    save_to: Optional local folder to save the DDY (Enhanced: 1 credit, needs EPWTOOLS_API_KEY).
    ddy_name: Base name for the saved DDY. Use the base name of an EPW saved by a generate_* tool to
              replace its DDY, so OpenStudio-MCP's change_building_location loads these design days.

Returns:
    JSON with the station, values (deg C), accuracy or 90 % ranges, and the saved DDY path.

Input parameters:

- `current_climate` (boolean)
- `ddy_name`
- `edition` (string)
- `lat` (number, required)
- `location_name`
- `lon` (number, required)
- `mode` (string)
- `save_to`

Output parameters:

- `result` (string)

### `list_cmip6_models` (~27 tokens)

Return the list of available CMIP6 GCM models for future climate generation.

Output parameters:

- `result` (string)

### `get_nearest_stations` (~98 tokens)

Return the n nearest active weather stations to a given coordinate.

Args:
    lat: Latitude in decimal degrees.
    lon: Longitude in decimal degrees.
    n: Number of stations to return (1–50).

Returns:
    JSON array of station objects with name, WMO, lat, lon, distance_km.

Input parameters:

- `lat` (number, required)
- `lon` (number, required)
- `n` (integer)

Output parameters:

- `result` (string)

### `get_job_result` (~57 tokens)

Check the status and result of any previously submitted job.

Args:
    job_id: The UUID returned by any generate_* tool.

Returns:
    JSON with status, logs, and result dict.

Input parameters:

- `job_id` (string, required)

Output parameters:

- `result` (string)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools#diagnostics

## Score history

- 2026-10-18: 66
- 2026-10-17: 65
- 2026-10-16: 66
- 2026-10-15: 65
- 2026-10-14: 65
- 2026-10-13: 64
- 2026-10-12: 49
- 2026-10-07: 58
- 2026-10-04: 58
- 2026-10-03: 58
- 2026-10-02: 58
- 2026-10-01: 58
- 2026-09-30: 58
- 2026-09-29: 43

## Common questions

### What is the EPW.tools MCP server?

EPW.tools is an MCP server listed in the public MCP registry as io.github.carlobianchi89/epwtools. EnergyPlus weather files (EPW, DDY, STAT) and design conditions for any site, OpenStudio-MCP ready. This page covers its PyPI package (epwtools).

### Is the EPW.tools MCP server safe to use?

EPW.tools scores 66 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 18 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the EPW.tools MCP server expose?

EPW.tools exposes 8 tools: generate_epw, generate_forecast, generate_tmy, generate_future_climate, get_design_conditions, and 3 more. Their descriptions and schemas cost roughly 1,852 tokens of context every time the server is loaded.

### Is the EPW.tools MCP server still maintained?

EPW.tools is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the EPW.tools MCP server under?

EPW.tools declares the Proprietary licence, which is not on the OSI-approved list. Read the terms before using it at work, and note this covers the source only, not the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/epwtools/
- Socket report: https://socket.dev/pypi/package/epwtools
- Website: https://epw.tools/ai-weather-files
- Changelog RSS feed: https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools.xml
- Changelog JSON feed: https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools.json
- HTML version of this page: https://verifymcp.io/servers/carlobianchi89-epwtools/epwtools