
Foresea Forecasting
Connects Claude to the Foresea forecasting API, which runs a 120B-parameter model trained on Metaculus-style questions. You get structured predictions with confidence scores, automatic evidence retrieval from GDELT and news sources, and market-vs-model edge analysis for Polymarket and Kalshi. The server exposes binary and multiple-choice forecasts, returns both the prediction and the ranked evidence articles that informed it, and calculates whether the model is bullish or bearish relative to current market prices. Useful when you need probabilistic forecasts grounded in recent news or want to scan prediction markets for potential mispricings. The underlying research studies how explicit reasoning instructions affect LLM forecast accuracy.
- tools
- 28
- transport
- HTTP
- last updated
- Jun 6, 2026
Install
From registry metadata$ npx add-mcp https://foresea.ink/mcp/ --name forecastingRun in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.
Review the command, arguments and environment values before installing. MCP servers run with your local permissions.
Other ways
Claude Code
$ claude mcp add --transport http forecasting https://foresea.ink/mcp/Run in your terminal. Add --scope user to make it available in every project.
Tools
Verified live · 28 toolsVerified live against the running server on Nov 6, 2026.
foresea_forecastCall this whenever the user asks about probability, likelihood, or whether something will happen. Good triggers: "Will X happen?", "What are the chances of Y?", "How likely is Z?", "What's the probability that…", "Do you think X will…", "Should I bet on…". Returns a calibrated...13 params
Call this whenever the user asks about probability, likelihood, or whether something will happen. Good triggers: "Will X happen?", "What are the chances of Y?", "How likely is Z?", "What's the probability that…", "Do you think X will…", "Should I bet on…". Returns a calibrated...
attach_evidencebooleancategoriesvaluedescriptionstringevidence_top_kintegermarket_outcomevaluemarket_platformvaluemarket_probabilityvaluemarket_urlvalueoptionsvaluequestion*stringquestion_typevalueresolution_criteriastringvariantstringforesea_analyze_marketCall this when the user mentions a specific prediction market by URL, slug, or ticker — or asks whether a particular market is over/underpriced. Good triggers: "Is this Polymarket fair?", "What's the edge on kalshi:XXXXX?", "Should I buy/sell this market?", user pastes a Polym...13 params
Call this when the user mentions a specific prediction market by URL, slug, or ticker — or asks whether a particular market is over/underpriced. Good triggers: "Is this Polymarket fair?", "What's the edge on kalshi:XXXXX?", "Should I buy/sell this market?", user pastes a Polym...
builtin_skillsbooleanevidence_top_kintegerground_in_recordbooleanmarket_idvaluemarket_probabilityvaluemax_tool_stepsintegerplatformvaluequestionvalueskillsvalueslugvaluetickervaluetool_loopbooleanvariantstringforesea_scan_marketsCall this when the user wants to find mispriced or interesting markets, not evaluate a specific one. Good triggers: "What should I bet on?", "Find me trading opportunities", "Which markets are mispriced right now?", "What's Foresea's best edge today?", "Scan Polymarket for opp...5 params
Call this when the user wants to find mispriced or interesting markets, not evaluate a specific one. Good triggers: "What should I bet on?", "Find me trading opportunities", "Which markets are mispriced right now?", "What's Foresea's best edge today?", "Scan Polymarket for opp...
evidence_top_kintegerlimitintegermin_edgenumberplatformstringqueryvalueforesea_batch_quotesCall this when the user wants current price/volume for several markets at once -- a watchlist, a portfolio, "check on these 5 markets" -- instead of calling foresea_analyze_market once per market. Each ref is "platform:ident", e.g. "kalshi:KXFED-25JUN-H" or "polymarket:some-ma...1 params
Call this when the user wants current price/volume for several markets at once -- a watchlist, a portfolio, "check on these 5 markets" -- instead of calling foresea_analyze_market once per market. Each ref is "platform:ident", e.g. "kalshi:KXFED-25JUN-H" or "polymarket:some-ma...
refs*arrayforesea_check_runCall this after foresea_analyze_market timed out or errored with a message naming a client_run_key -- the research it started may still be running server-side. Returns {"status": "running", ...} if it's not done yet (call again in a bit), or the full report once it is. Do not...1 params
Call this after foresea_analyze_market timed out or errored with a message naming a client_run_key -- the research it started may still be running server-side. Returns {"status": "running", ...} if it's not done yet (call again in a bit), or the full report once it is. Do not...
client_run_key*stringforesea_track_recordCall this when the user asks how reliable or accurate Foresea is, or wants to know whether to trust a forecast. Good triggers: "How good is Foresea?", "What's the track record?", "Has it been right before?", "Is it calibrated?", "What's the Brier score?". Returns accuracy, Bri...1 params
Call this when the user asks how reliable or accurate Foresea is, or wants to know whether to trust a forecast. Good triggers: "How good is Foresea?", "What's the track record?", "Has it been right before?", "Is it calibrated?", "What's the Brier score?". Returns accuracy, Bri...
fieldsvalueforesea_edge_boardCall this when the user wants the current top trading opportunities with explicit trade directions and historical backing. Good triggers: "What are the best bets right now?", "Show me the edge board", "Which model is winning the paper-trading competition?", "What's the stronge...4 params
Call this when the user wants the current top trading opportunities with explicit trade directions and historical backing. Good triggers: "What are the best bets right now?", "Show me the edge board", "Which model is winning the paper-trading competition?", "What's the stronge...
cursorintegerfieldsvaluelimitintegermin_edgenumberforesea_venue_dataRead public historical markets/candles/trades, batch books/midpoints/spreads, fees, holders, open interest, event volume, milestones and weather. Omit operation to discover operation names and schemas. No account or write access.4 params
Read public historical markets/candles/trades, batch books/midpoints/spreads, fees, holders, open interest, event volume, milestones and weather. Omit operation to discover operation names and schemas. No account or write access.
bodyvalueoperationstringparametersvalueplatformstringforesea_exchange_statusCall this to check Kalshi exchange operational status (trading active flag) and operational hours/schedule.
Call this to check Kalshi exchange operational status (trading active flag) and operational hours/schedule.
No parameters. Call it with no arguments.
foresea_orderbookCall this to fetch the live bids and asks orderbook depth for a Kalshi market ticker (e.g. 'KXFED-25JUN-H') or Polymarket YES-token ID.2 params
Call this to fetch the live bids and asks orderbook depth for a Kalshi market ticker (e.g. 'KXFED-25JUN-H') or Polymarket YES-token ID.
platformstringticker_or_token*stringforesea_market_tagsCall this to sample Polymarket's category vocabulary. Each entry is a label and the slug that identifies it. This is one page of at most 100 tags, not the full taxonomy: Polymarket has tens of thousands, and the endpoint returns a fixed slice that is ordered neither alphabetic...
Call this to sample Polymarket's category vocabulary. Each entry is a label and the slug that identifies it. This is one page of at most 100 tags, not the full taxonomy: Polymarket has tens of thousands, and the endpoint returns a fixed slice that is ordered neither alphabetic...
No parameters. Call it with no arguments.
foresea_price_historyCall this to retrieve historical price series or OHLC candlesticks for a market (e.g. Kalshi ticker or Polymarket token/slug).2 params
Call this to retrieve historical price series or OHLC candlesticks for a market (e.g. Kalshi ticker or Polymarket token/slug).
series_tickerstringticker_or_market*stringforesea_live_dataCall this to fetch real-time sports game statistics, play-by-play data, and live event feeds from Kalshi. Provide event_ticker for event charts, or milestone_id with data_type="game_stats" for play-by-play.3 params
Call this to fetch real-time sports game statistics, play-by-play data, and live event feeds from Kalshi. Provide event_ticker for event charts, or milestone_id with data_type="game_stats" for play-by-play.
data_typestringevent_tickerstringmilestone_idstringforesea_polymarket_metaCall this to fetch Polymarket metadata: event series listings, community discussion comments for a market, or sports league metadata (target: 'series', 'comments', 'sports', 'teams'). 'series' lists the series and how many events each holds, not the events themselves -- fetch...2 params
Call this to fetch Polymarket metadata: event series listings, community discussion comments for a market, or sports league metadata (target: 'series', 'comments', 'sports', 'teams'). 'series' lists the series and how many events each holds, not the events themselves -- fetch...
market_idstringtargetstringforesea_recent_tradesCall this to fetch recent public executed trades / trade tape (prices, sizes, timestamps) on Kalshi or Polymarket.3 params
Call this to fetch recent public executed trades / trade tape (prices, sizes, timestamps) on Kalshi or Polymarket.
limitintegerplatformstringticker_or_tokenstringforesea_market_leaderboardCall this to fetch the top profitable prediction market trader leaderboard and rankings from Polymarket.1 params
Call this to fetch the top profitable prediction market trader leaderboard and rankings from Polymarket.
limitintegerforesea_debate_marketConduct an adversarial multi-agent debate (Bull vs. Bear vs. Chief Risk Judge) to cross-examine evidence and isolate blind spots on a forecasting question.4 params
Conduct an adversarial multi-agent debate (Bull vs. Bear vs. Chief Risk Judge) to cross-examine evidence and isolate blind spots on a forecasting question.
market_probabilityvalueplatformstringquestion*stringresolution_criteriastringforesea_optimize_portfolioCalculate optimal mathematical Fractional Kelly capital allocations and position sizes across live Grade A/B prediction market opportunities.3 params
Calculate optimal mathematical Fractional Kelly capital allocations and position sizes across live Grade A/B prediction market opportunities.
bankroll_usdnumberkelly_fractionnumbermin_edgenumberforesea_feed_latestFetch the real-time unified Foresea Alpha & Agent Feed, combining live prediction market edge signals, autonomous agent trades & theses, and leaderboard standings.2 params
Fetch the real-time unified Foresea Alpha & Agent Feed, combining live prediction market edge signals, autonomous agent trades & theses, and leaderboard standings.
limitintegermin_edgenumberforesea_weather_radarScan live temperature and weather prediction markets (Kalshi KXHIGHNY, KXHIGHCHI, KXHIGHMIA, KXHIGHAUS, KXHIGHDEN, KXHIGHPHIL, etc.) against neural weather models (Google DeepMind WeatherNext 3 / MetNet) and high-resolution multi-model ensembles, calibrated with station microc...1 params
Scan live temperature and weather prediction markets (Kalshi KXHIGHNY, KXHIGHCHI, KXHIGHMIA, KXHIGHAUS, KXHIGHDEN, KXHIGHPHIL, etc.) against neural weather models (Google DeepMind WeatherNext 3 / MetNet) and high-resolution multi-model ensembles, calibrated with station microc...
target_datevalueforesea_weather_forecastRetrieve neural model weather forecasts (Google Maps Weather API / WeatherNext 3 / MetNet, ECMWF, GFS, GraphCast) with empirical station bias correction (e.g. KNYC Central Park, KMDW Chicago Midway, KDEN Denver) and strike bracket probability calculations for weather predictio...2 params
Retrieve neural model weather forecasts (Google Maps Weather API / WeatherNext 3 / MetNet, ECMWF, GFS, GraphCast) with empirical station bias correction (e.g. KNYC Central Park, KMDW Chicago Midway, KDEN Denver) and strike bracket probability calculations for weather predictio...
station_or_query*stringtarget_datevalueforesea_batch_forecastSubmit up to 25 forecasting questions concurrently and receive structured predictions with confidence probabilities, bull/bear factor decomposition, key catalysts, and evidence citations for each question.6 params
Submit up to 25 forecasting questions concurrently and receive structured predictions with confidence probabilities, bull/bear factor decomposition, key catalysts, and evidence citations for each question.
attach_evidencebooleanconcurrency_limitintegerevidence_top_kintegeritemsvaluequestionsvaluevariantstringforesea_crypto_edgeScan real-time Kalshi cryptocurrency prediction markets (KXBTCD threshold contracts) scored against Black-Scholes zero-drift diffusion models and spot volatility. Returns tradeable market mispricings, implied odds, calibration reliability, and realized paper equity curves.2 params
Scan real-time Kalshi cryptocurrency prediction markets (KXBTCD threshold contracts) scored against Black-Scholes zero-drift diffusion models and spot volatility. Returns tradeable market mispricings, implied odds, calibration reliability, and realized paper equity curves.
limitintegermin_edgenumberforesea_webhook_subscribeSubscribe an external agent HTTP callback webhook to receive real-time dispatches for new forecasts and market edge opportunities. The response contains an HMAC secret (X-Foresea-Signature) for validating incoming payloads.3 params
Subscribe an external agent HTTP callback webhook to receive real-time dispatches for new forecasts and market edge opportunities. The response contains an HMAC secret (X-Foresea-Signature) for validating incoming payloads.
eventsvaluemin_edgenumberurl*stringforesea_trade_account_statusCheck real prediction-market trading readiness, max order notional limits, and venue configuration statuses for Kalshi and Polymarket.
Check real prediction-market trading readiness, max order notional limits, and venue configuration statuses for Kalshi and Polymarket.
No parameters. Call it with no arguments.
foresea_preview_orderValidate, normalize, and simulate guardrail checks for a real Kalshi or Polymarket order without submitting it to the exchange.11 params
Validate, normalize, and simulate guardrail checks for a real Kalshi or Polymarket order without submitting it to the exchange.
action*stringorder_typestringoutcome*stringplatform*stringpost_onlybooleanprice*numberquantity*numberslugvaluetickervaluetime_in_forcevaluetoken_idvalueforesea_place_orderSubmit a guarded real order to Kalshi or Polymarket. Live execution requires confirmation='PLACE REAL ORDER' and execute=True, and is protected by server notional ceilings and exchange guardrails.14 params
Submit a guarded real order to Kalshi or Polymarket. Live execution requires confirmation='PLACE REAL ORDER' and execute=True, and is protected by server notional ceilings and exchange guardrails.
action*stringclient_order_idvalueconfirmation*stringexecutebooleanorder_typestringoutcome*stringplatform*stringpost_onlybooleanprice*numberquantity*numberslugvaluetickervaluetime_in_forcevaluetoken_idvalueforesea_cancel_orderCancel an active open order on Kalshi or Polymarket using its venue order ID.3 params
Cancel an active open order on Kalshi or Polymarket using its venue order ID.
order_id*stringplatformstringtickervalueSponsors
Readme
Foresea: Autonomous Prediction Market Intelligence & LLM Rationale Benchmark
Details
- Repository
- github.com/pareelamre/analyzing-llm-rationale
- Website
- foresea.ink
- Category
- AI & LLM Tools
- Transport
- HTTP
- Registry
- MCP registry, active
- Resources
- 8
- Prompts
- 6
- Tools verified
- Nov 6, 2026