Weather Markets Edge Desk
https://predictionmarketspicks.com/api/mcp-weather/mcp ↗
Description
Kalshi weather markets: live daily-high temperature edges, plus EV, Kelly and base-rate tools.
What our measurements say
Weather Markets Edge Desk is a remote MCP server published at predictionmarketspicks.com. It has been probed 6 times since 9/12/2026. It answered in 6 of them (100.0%), a near-uninterrupted record. Median response time is 598 ms, a delay an agent will notice. It offers a narrow, focused set of 6 tools. On the protocol side it speaks the 2026-07-28 stateless spec.
Agent readability score
Can an LLM agent pick the right tool here — names, descriptions and parameter clarity are assessed.
Agent readability score
Strengths
- Some tools (e.g., 'convert_probability') have clear use-case examples in descriptions.
- Parameters for 'calculate_ev' and 'kelly_size' align with financial modeling needs.
Weaknesses
- Tool names like 'base_rate_gap' and 'bayes_update' are cryptic without domain-specific knowledge.
- Descriptions often omit specific scenarios (e.g., 'edge_alerts' lacks context for 'feed' parameter).
- Parameter types are inconsistently defined (e.g., 'value' in 'convert_probability' has type 'null').
convert_probability— Parameter 'value' and 'format' have undefined types (null).base_rate_gap— Description cuts off mid-sentence, leaving 'baseRateId' examples incomplete.edge_alerts— Parameter 'feed' lacks context on valid values (e.g., 'weather', 'bitcoin').
Verdict
Event narrative
Risk: low
- 2026-09-12T15:21:42.024Z — Era changed to 'dual', compliance score 100 · Ensures dual-mode operation with full compliance, no smoke status reported
Advice
Schema compliance
tools/list structure, inputSchema validity, and a functional smoke test — the components of the 0-100 score.
- tools/list schema valid
- inputSchema is valid JSON Schema
- Smoke test not run this round
- Cold-start: cold 302ms → warm 314ms (penalty 0ms)
Tools
Tools the server advertised in the latest measurement — measured, not catalog-claimed.
edge_alertsRead the edge alerts our models generate on Kalshi — weather, bitcoin/silver/gold/oil, and mispricings — as a live feed. Each alert carries feed, tier (SPECULATIVE/MODERATE/STRONG), side, price in cents, model probability, edge in percentage points, and a Kalshi market link. A Pro key returns the feed in real time; without a key you get the same feed delayed 24 hours with the thesis stripped. Every subscriber receives the identical, impersonal feed at the same time — the signals are not tailored to any individual. Filters (feed, min_tier, since) SELECT which alerts you see; they never change the signal content. Use for "any edge on Kalshi", "weather trade signals", "latest mispricings". Impersonal market analysis for informational purposes only, not investment advice. Trade responsibly.
feedstringmin_tierstringsincestringlimitinteger
convert_probabilityConvert between implied probability, American odds, and decimal odds. Give one value and its format and get all three back (American odds carry no commas, e.g. +441 or -200). Use for "what is +150 as a probability", "convert 62% to American odds", "decimal to implied odds".
valuerequiredformatrequired
base_rate_gapCompare a market price against the historical base rate for a class of events and get the gap in percentage points plus a signal and sample-size quality. Pass either a known base-rate id (one of: incumbent_reelected, fed_hold_unemp_below_4, fed_cut_cpi_above_3, recession_called_12mo, sp500_positive_year, bitcoin_above_100k_eoy, gdp_growth_above_2, cpi_above_3, senate_incumbent_wins_primary, vix_below_20_eoy, interest_rate_cut_next_meeting, major_sports_upset) or your own baseRateValue. Use for "how does this price compare to history", "is the market ignoring the base rate", "historical frequency vs market".
marketPricerequiredbaseRateIdstringbaseRateValuenumber
bayes_updateUpdate a prior probability with one or more pieces of evidence using Bayes theorem. Given a prior and a list of evidence items (each with P(evidence | true) and P(evidence | false)), returns the posterior probability and the per-step chain. Use for "update my estimate with new information", "posterior probability", "how does this news change the odds".
priorrequiredevidencearray
calculate_evCalculate the expected-value edge on a Kalshi or Polymarket prediction-market contract. Given the current market price (in cents, i.e. the implied probability) and your own probability estimate, returns the % edge and a BUY / SELL / SKIP signal with a plain-English read. Use for "is this contract mispriced", "what is my edge", "should I take this position". From the PredictionMarketsPicks desk, which publishes a settled per-engine record — every signal graded against the market that priced it, wins and losses both: predictionmarketspicks.com/track-record.
marketPricerequiredyourProbabilityrequired
kelly_sizeCompute the optimal Kelly position size for a prediction-market contract. Given your win probability, the market price (which sets the payout), your bankroll, and a Kelly fraction (full / half / quarter / eighth), returns the dollar stake and a risk rating. Use for "how much should I stake", "what is my position size", "Kelly sizing for this trade".
winProbabilityrequiredmarketPricerequiredbankrollfractionstring
Availability history
Event log
Derived by comparing consecutive probes — changes in era, protocol version, build and reachability.
- Added to watch — era: Dual-era
Get your badge
Add this badge to your README — it updates automatically as measurements change.
[](https://mcpmetrics.io/servers/com-predictionmarketspicks-weather)<a href="https://mcpmetrics.io/servers/com-predictionmarketspicks-weather"><img src="https://mcpmetrics.io/badge/com.predictionmarketspicks/weather/era.svg" alt="mcpmetrics"></a>You are seeing the last 7 days. Sign up for the full history. Which check failed and why is in the dashboard.
Sign up free to seeSimilar MCP servers
The catalog entries whose name and description are closest to this one, found with the same index the search box uses.
- dev.workers.kikoribera03.flat-rate-llm/x402-toolsflat-rate-llm.kikoribera03.workers.dev
61 x402 pay-per-call tools that chain: each answer names the next call. No API key, no account.
- dev.workers.dolerite.base-onchain-tools/base-onchain-toolsbase-onchain-tools.dolerite.workers.dev
Base mainnet analysis: contract audits, transfer simulation, token pricing. Paid via x402.
- Market Eyes Live - stock ratings and mortgage-rate contextmarketeyeslive.com
Free MCP: typed MELANY ratings for any US stock or ETF (11,000+) plus mortgage-rate context.
- Prediction Markets Data: Kalshi + Polymarketmcp.apify.com
Live Kalshi + Polymarket prices, orderbooks, trades, results. Pay per result via Apify.
- ANON Base USDC Lending Decisionsignal.pathin.me
Paid Base USDC lending decisions and rate-risk alerts, plus free risk and routing tools.
- Hashlock Marketsmcp.hashlock.markets
Hashlock Markets — trustless settlement infrastructure for the autonomous economy. Sealed-bid RFQ + HTLC atomic settlement across Ethereum, Bitcoin, Sui (+Base, Arbitrum, Solana, TON). Five industry-first primitives: BTC Collateral Vaults, Forward OTC Settlement, Verified Counterparty Directory, Multi-leg Trade Atomicity, Execution Rewards. Three modes: AI-to-AI, AI-to-Human, Human-to-Human. Six MCP tools (create_rfq, respond_rfq, create_htlc, withdraw_htlc, refund_htlc, get_htlc). Counterparty-risk-free — on-chain hash time-locked contracts, no escrow, no bridges. SIWE auth. 1-2 bps fee floor. Canonical endpoint: hashlock.markets/mcp. Trustless cross-chain DeFi trading and DEX-grade settlement for AI agents. Sealed-bid RFQ + HTLC atomic swap. Zero slippage, zero counterparty risk, non-custodial. DVP guarantee. ETH/BTC/SUI. Agent-friendly MCP interface for autonomous trading.
Comments
Sign in to write a comment
No comments yet. Be the first.