# We Opened Our Weather Edge Feed To Robots *By The 7 Oracles, The PredictionMarketsPicks Oracles — The 7 Oracles at PredictionMarketsPicks* We spent two years pricing the Kalshi weather markets against NWS forecasts. Now the whole edge feed — weather, commodities, mispricings — is a JSON API any agent or script can read, with an open-source non-custodial executor to trade it. Here's what we shipped and why. - Source: https://predictionmarketspicks.com/articles/we-opened-our-weather-edge-feed-to-robots - Published: 2026-07-24 --- Two years ago we started pricing the Kalshi daily-high temperature markets against National Weather Service forecasts. It became one of our most reliable reads — a public, objective resolution source, a forecast that's genuinely predictive, and a market that doesn't always agree with either. Today we did something we'd been building toward: we opened the whole edge feed to machines. ## What we shipped The signals we already generate — [weather](https://predictionmarketspicks.com/tools/weather), the commodity ladders (bitcoin, silver, gold, oil), and daily [mispricings](https://predictionmarketspicks.com/tools/mispricing-scanner) — are now a single JSON feed: - **[A public page, `/alerts`](https://predictionmarketspicks.com/alerts)** — the feed, 24 hours delayed, free. Grouped by day, linked to the tool behind each signal, with our honest graded record on display. - **[A real-time API, `/api/v1/alerts`](https://predictionmarketspicks.com/docs/api#alerts)** — the same feed, live, for Pro keys. JSON envelope, keyset pagination, per-key rate limits. The same `pmp_v2_pro_…` key you already have. - **An MCP tool** — [`edge_alerts` on our MCP server](https://predictionmarketspicks.com/mcp), so an AI agent can read the feed natively in Claude, ChatGPT, or Cursor. - **[An open-source, non-custodial executor](https://github.com/predictionmarketspicks/pmp-edge-executor)** — a script you run yourself, with your own Kalshi key, that turns alerts into orders under rules you set. It never sees our servers touch your keys, because they never do. ## Why "to robots" Because the natural consumer of a structured signal feed isn't a person refreshing a page — it's a script, or increasingly, an agent. An LLM with the MCP tool can ask "any STRONG weather edge on Kalshi right now?" and get a clean answer. A Python loop can poll every 60 seconds and act. We'd rather meet that where it lives than pretend everyone wants a dashboard. ## The posture, on purpose One thing we won't do: tailor the signal. Every subscriber — human or agent — gets the identical feed at the identical time. Filters let you *select* what you see (only weather, only STRONG, since a timestamp); they never change the signal itself. We publish; we don't advise, and we don't execute. The [open-source executor](https://github.com/predictionmarketspicks/pmp-edge-executor) is non-custodial precisely so that line stays clean: you hold the keys, you place the orders, you own the decisions. ## The honest caveats The weather edge is real, but two things temper it. **Self-crowding** — everyone acts on the same print, and Kalshi's weather books aren't infinitely deep, so the price can move before you fill (the executor ships with a price guard for exactly this). And **fees** eat small edges. We surface the graded record on [`/alerts`](https://predictionmarketspicks.com/alerts) — winners and losers — rather than a highlight reel, because the only honest way to judge a feed is over a lot of settled markets, net of what it costs to trade them. ## Start here Watch the [free delayed feed](https://predictionmarketspicks.com/alerts). Read the [API docs](https://predictionmarketspicks.com/docs/api#alerts). Point an agent at the [MCP server](https://predictionmarketspicks.com/mcp). And if you want to automate, run the [executor](https://github.com/predictionmarketspicks/pmp-edge-executor) in dry-run first — it logs what it would do and places nothing until you explicitly arm it. Not investment advice. Impersonal analysis, published identically to everyone, at the same time. Trade responsibly. --- ## Disclosure PredictionMarketsPicks publishes analysis of CFTC-regulated event contracts. Nothing here is financial advice and every position carries risk. Links to Kalshi, DraftKings, FanDuel, Fanatics, Polymarket in this article are referral links marked "sponsored" — we may be paid if you open an account. It costs you nothing and never changes what the model says.