SNOTEL

Provides access to real-time and historical SNOTEL weather and snow data via MCP for AI assistants.
  • python

1

GitHub Stars

python

Language

5 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs
{
  "mcpServers": {
    "jymmyt-snotel-mcp-server": {
      "command": "python",
      "args": [
        "-m",
        "snotel_mcp_server"
      ],
      "env": {
        "LOGLEVEL": "INFO",
        "AWDB_TIMEOUT": "30",
        "AWDB_API_BASE": "https://wcc.sc.egov.usda.gov/awdbRestApi"
      }
    }
  }
}

You can access real-time and historical SNOTEL weather and snow data through a dedicated MCP server built with FastMCP. This enables AI assistants to query thousands of SNOTEL stations, retrieve measurements like snow depth and precipitation, and analyze snowpack trends via an MCP client in a structured, programmable way.

How to use

Use an MCP client to interact with the SNOTEL MCP Server and perform practical data tasks. You can discover nearby or state-specific stations, fetch detailed station information, pull raw data over custom date ranges, retrieve the latest conditions, and analyze snowpack trends. Each tool is exposed as an endpoint you call through MCP, returning structured results you can display in dashboards, assistants, or automation flows.

Typical usage patterns include: find stations by location or state to identify relevant sites, request recent conditions to monitor current snow and weather, pull historical data for analysis, and run snowpack trend analyses for specified date ranges. Combine these capabilities to build seasonal summaries, storm event logs, or daily condition dashboards for your team or application.

How to install

# Prerequisites
# - Python 3.9+
# - uv package manager (recommended) or pip

# Quick Start
# Prerequisites: ensure Python 3.9+ is installed

# Clone the repository
git clone https://github.com/example/snotel-mcp-server.git
cd snotel-mcp-server

# Create and activate virtual environment with uv
uv venv
source .venv/bin/activate  # On Windows: .venv\Scripts\activate

# Install dependencies
uv pip install -e .

# Or install development dependencies
uv pip install -e ".[dev]"
# Running the server

# Run with default stdio transport
python -m snotel_mcp_server

# Or if installed
snotel-mcp-server
{
  "mcpServers": {
    "snotel": {
      "command": "python",
      "args": ["-m", "snotel_mcp_server"],
      "cwd": "/path/to/snotel-mcp-server"
    }
  }
}

Additional sections

Configuration and runtime behavior are designed to be straightforward for MCP clients. FastMCP handles transport setup by default, so you can focus on crafting queries to obtain station data, recent conditions, and trend analyses.

Tools and endpoints

The MCP server exposes a set of endpoints you can call from an MCP client to perform common tasks. Available tools include finding stations, getting station information, retrieving station data, obtaining recent conditions, and analyzing snowpack trends. Each tool returns structured data suitable for display and further processing in AI assistants.

Notes

  • Use the two provided run configurations to start the server locally via Python or the installed command. - Ensure network access to the USDA AWDB REST API for data retrieval. - You can enable verbose logging to diagnose issues by setting the log level when starting the server.

Available tools

find_snotel_stations

Find SNOTEL stations by state or geographic location with optional radius and network type.

get_station_info

Get detailed information about a specific SNOTEL station using its station triplet.

get_station_data

Retrieve raw snow and weather data from a station for a given date range and set of elements.

get_recent_conditions

Get recent conditions for a station over a specified number of days.

analyze_snowpack_trends

Analyze snowpack trends and statistics for a station over a date range.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational