nephyr-weather

GFS ensemble weather signals for prediction market edge detection.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Get Weather Signals: Get GFS ensemble weather signals for one or more cities on a given date. Returns model probability of daily high exceeding various thresholds, derived from the 31-member GFS ensem
  • Get Ensemble Forecast: Fetch the raw GFS 31-member ensemble forecast for a city on a given date. Returns per-member daily high temperatures, low temperatures, and precipitation. Useful for custom prob
  • Detect Edges: Scan weather markets for edges — cases where the GFS model probability differs significantly from the market-implied probability. Requires a list of (signal, market) pairs. Returns all E

What data it sees

Do you need an account

No: the server works without sign-in

GFS ensemble weather signals for prediction market edge detection. Generate weather-based trading signals across 12 major cities, retrieve multi-day forecasts, calculate prediction market edges from weather data, and discover active weather-related markets. Turn meteorological data into actionable market intelligence.

How to connect

How to connect nephyr-weather to Claude

The server address to paste into Claude settings:

https://nephyr-weather--clm-studios.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect nephyr-weather to ChatGPT

The server address to paste into ChatGPT settings:

https://nephyr-weather--clm-studios.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect nephyr-weather to Cursor

The server address to paste into Cursor settings:

https://nephyr-weather--clm-studios.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (5)

Raw names from tools/list. Only developers need these.

get_weather_signalsGet GFS ensemble weather signals for one or more cities on a given date. Returns model probability of daily high exceeding various thresholds, derived from the 31-member GFS ensemble forecast. Requires cities (list of city names) and forecast_date (YYYY-MM-DD). Optional: threshold_f (temperature threshold, default 70), direction (above/below, default above), market_type (high/low/rain, default high).
get_ensemble_forecastFetch the raw GFS 31-member ensemble forecast for a city on a given date. Returns per-member daily high temperatures, low temperatures, and precipitation. Useful for custom probability calculations or verifying signal generation.
detect_edgesScan weather markets for edges — cases where the GFS model probability differs significantly from the market-implied probability. Requires a list of (signal, market) pairs. Returns all EdgeResults, or only tradeable ones if tradeable_only=True.
list_active_marketsList active weather markets on Polymarket or Kalshi. Optionally filter by city. Returns market tickers, prices, volumes, and metadata. Kalshi requires api_key to be provided.
get_city_infoGet coordinates and metadata for a supported city, or list all supported cities if no city is provided.