extract_f6_csvLABSCO SUMMARY
The F6 extraction is what a PDF archive needed.
Two decades of monthly climate forms are only useful if you can get the daily table out of them, and extract_f6_csv is exactly that — the difference between an archive you can cite and one you can compute over. Everything else is exposed as resources rather than tools, which suits data a model wants to read rather than act on.
What it is
A Python server that exposes the Mt Washington Observatory's public data. Current conditions, the full forecast package and the historical F6 climate forms all arrive as MCP resources, with two tools for turning the F6 PDFs into something a model can actually read.
What you get
weather://currentreturns summit temperature, wind, gusts, direction and METARweather://outlook/summitandweather://outlook/valleyreturn the Higher Summits and Valley forecasts, each with a four-period discussionweather://outlook/statisticscovers the past 24 hours — max and min temperature, peak gust, precipitation, snowfall;weather://outlook/almanaccovers records, monthly averages and sunrise/sunsetf6://currentandf6://{year}/{month}return the F6 monthly PDF forms, available from 2005 onwardextract_f6_csv(year, month)pulls the F6 daily data table out as CSV;list_f6_forms()lists every year and month combination available
Requirements
Python 3.14 or newer and uv. Clone the repository, run uv sync, then uv run mtw-obs-mcp — or uv run python -m mt_washington_mcp, which does the same thing. Stdio transport. No account and no key: the data comes from the Observatory's public endpoints.
Setup effort
Build from source — git clone https://github.com/spowers42/mt_washington_obs_mcp
USE CASES
01
Checking what it is doing on the summit right now
Read the current conditions with the wind, gusts and METAR.
02
Deciding whether tomorrow is climbable
Read the Higher Summits forecast and its four-period discussion.
03
Looking up how a past month actually went
List the available F6 forms, then pull that month's daily table as CSV.
04
Putting today in context
Read the almanac records and monthly averages alongside the current conditions.
2 tools
Listed in project docs. Your client may show a different list.
list_f6_formsBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
Python 3.14+
INSTALLATION
Connect your client
Server setup
TERMINAL
git clone https://github.com/spowers42/mt_washington_obs_mcp
cd mt_washington_obs_mcp
uv sync
uv run mtw-obs-mcpThe README gives no client configuration. It says the server runs over stdio with uv run mtw-obs-mcp from the cloned folder and can be connected to an MCP client such as Claude Desktop or opencode — add it in the format your client expects.
