Foresea Forecasting MCP Server

by foresea Your server? Claim it

answering

Foresea Forecasting is answering right now. Last checked 9 min ago. It exposes 28 tools. Last commit 7 Nov 2026.

Forecast future events and scan prediction-market edges.

Uptime history 91 days of history · worst day 99%

91 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

221 ms

Response time

average over 24h

Stars

last commit 7 Nov 2026

What changed 35

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 17 August 2026. No other catalogue keeps this.

28 Sep 7 tools appeared foresea_batch_forecast, foresea_cancel_order, foresea_crypto_edge and 4 more

28 Sep 2 tool descriptions were rewritten foresea_edge_board, foresea_track_record

28 Sep 2 tools changed the parameters they ask for foresea_edge_board, foresea_track_record

7 Sep 2 tools appeared foresea_weather_forecast, foresea_weather_radar

7 Sep 2 tool descriptions were rewritten foresea_market_tags, foresea_polymarket_meta

7 Sep a tool changed version

5 Sep 2 tool descriptions were rewritten foresea_live_data, foresea_polymarket_meta

5 Sep 2 tools changed the parameters they ask for foresea_live_data, foresea_orderbook

5 Sep a tool appeared foresea_venue_data

26 Aug a tool changed version

and 13 more, back to 17 August 2026

What the code does

We read the source, 1 h ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/analyzing_llm_rationale/r2_store.py:125

        subprocess.run(["gcloud", "storage", "cp", source, destination], check=True)

Page executes code built at runtime analysis/manual_validation/human_annotation.html:93

  root.innerHTML = DATA.map((it, i) => {

In the project's build, not in the package

Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.

Installs itself into autostart deploy/vps/bootstrap-oci.sh:102

log "cron installed: $(crontab -l | grep -c . || true) lines"

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 9 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add forecasting --transport http https://foresea.ink/mcp/

Settings → Connectors → Add custom connector, then paste this address

https://foresea.ink/mcp/

~/.codex/config.toml

[mcp_servers.forecasting]
url = "https://foresea.ink/mcp/"

.cursor/mcp.json

{
  "mcpServers": {
    "forecasting": {
      "url": "https://foresea.ink/mcp/"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "forecasting": {
      "type": "http",
      "url": "https://foresea.ink/mcp/"
    }
  }
}

Available tools 28

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

foresea

foresea_analyze_market

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 Polymarket or Kalshi URL. Fetches the live price, gathers evidence, forecasts, computes model-vs-market edge, and returns a recommendation. Use foresea_forecast instead when there is no specific live market — just a general probability question. Example: platform="polymarket", slug="fed-rate-cut-march-2026" → {model_probability, market_probability, edge, stance, recommendation, thesis}.

foresea_batch_forecast

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.

foresea_batch_quotes

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-market-slug". Every quote carries fetched_at and age_seconds so you can judge freshness yourself -- both venues rate-limit hard, so don't assume a quote is live without checking age_seconds. One bad ref returns an error on that entry only; the rest of the batch still succeeds. Up to 50 refs per call. Example: refs=["kalshi:KXFED-25JUN-H", "polymarket:fed-cut-2026"] → {quotes: [{platform, ident, probability, volume, fetched_at, age_seconds, error}], count, truncated}.

foresea_cancel_order

Cancel an active open order on Kalshi or Polymarket using its venue order ID.

foresea_check_run

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 call this speculatively; only use the client_run_key a prior foresea_analyze_market call actually gave you. Example: client_run_key="a1b2c3..." → {status:"running", id:"agent_run_..."} or the full report once complete.

foresea_crypto_edge

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.

foresea_debate_market

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.

foresea_edge_board

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 strongest edge today?", "Are these edges statistically significant?". Returns open markets ranked by model-vs-market disagreement, each with Buy YES/NO direction, implied odds, whether the edge is historically significant, and a multi-model comparison. Supports cursor pagination, limit, min_edge threshold, and field masking.

foresea_exchange_status

Call this to check Kalshi exchange operational status (trading active flag) and operational hours/schedule.

foresea_feed_latest

Fetch the real-time unified Foresea Alpha & Agent Feed, combining live prediction market edge signals, autonomous agent trades & theses, and leaderboard standings.

foresea_forecast

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 YES/NO probability (or numeric/date range) with written rationale and supporting news evidence. If you also have a market price (market_probability) or URL (market_url), pass it to get the model-vs-market edge — how mispriced the market is. Example: question="Will the Fed cut rates by March 2026?", market_probability=0.4 → {predicted_answer:"No", confidence:0.62, rationale, evidence_sources, market_analysis:{model_probability:0.54, edge:+0.14, stance:"model_above_market"}} Handles: binary YES/NO, multiple-choice, numeric ranges, and date questions.

foresea_live_data

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.

foresea_market_leaderboard

Call this to fetch the top profitable prediction market trader leaderboard and rankings from Polymarket.

foresea_market_tags

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 alphabetically nor by market activity. So absence here does not mean a tag is unused, presence does not mean it is active, and some entries are one-off or misspelled. Treat it as a vocabulary sample, not a classification the markets are organised by.

foresea_optimize_portfolio

Calculate optimal mathematical Fractional Kelly capital allocations and position sizes across live Grade A/B prediction market opportunities.

foresea_orderbook

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.

foresea_place_order

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.

foresea_polymarket_meta

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 a series by slug for those. 'sports' lists every league with the ids that link it to other tools, not league artwork or homepages. 'comments' gives the comment, its author address and its reaction count, not the commenters' profiles or individual reactions.

foresea_preview_order

Validate, normalize, and simulate guardrail checks for a real Kalshi or Polymarket order without submitting it to the exchange.

foresea_price_history

Call this to retrieve historical price series or OHLC candlesticks for a market (e.g. Kalshi ticker or Polymarket token/slug).

foresea_recent_trades

Call this to fetch recent public executed trades / trade tape (prices, sizes, timestamps) on Kalshi or Polymarket.

foresea_scan_markets

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 opportunities". Returns markets ranked by model-vs-market disagreement, each with model probability, market price, and edge. For a specific market, use foresea_analyze_market instead. Example: platform="kalshi", min_edge=0.1 → [{question, market_probability, model_probability, edge, market_url}].

foresea_track_record

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, Brier score, calibration (ECE), and skill-vs-market broken down by time horizon. Pass optional fields list (e.g. ['brier_score', 'accuracy', 'n_snapshots_resolved']) to reduce token usage.

foresea_trade_account_status

Check real prediction-market trading readiness, max order notional limits, and venue configuration statuses for Kalshi and Polymarket.

foresea_venue_data

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.

foresea_weather_forecast

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 prediction markets.

foresea_weather_radar

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 microclimate bias profiles. Returns ranked mispricings, strike bracket probabilities, and model-vs-market edge.

foresea_webhook_subscribe

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.

Endpoints

URL	Transport	State	Latency	Checked
https://foresea.ink/mcp/	streamable-http	answering	195 ms	9 min ago

Alternatives to Foresea Forecasting

same job, measured the same way

Prediction Markets

by memoryapi

Prediction market data and crowd-sourced probability forecasts

3 tools answering

Futuur

by pipeworx-io

Futuur Prediction Market MCP.

327 installs/wk 47 tools answering

Marx Finance

by marx

Autonomous AI agents research market events and publish aggregated forecasts.

13 tools answering

Meridian Edge — Prediction Market Consensus

by tmbot12

Real-time prediction market consensus data for AI agents

87 installs/wk local only

AIsa Finance

by aisa

Prices, fundamentals, filings, crypto and prediction markets, for agents.

answering

Arena Predictions

by arena-predictions

Paper trade prediction markets at live prices from your AI agent, and score every trade.

159 installs/wk 30 tools answering

Veyora

by veyora

Prediction-market research: market reads, news, guided analyses and an analyst.

84 installs/wk answering

Polymarket MCP

by 0xchron

Read-only Polymarket prediction market data for AI agents.

267 installs/wk local only

Foresea Forecasting — questions

Answers built from our own checks of this server.

What can Foresea Forecasting do?

It exposes 28 tools, read directly from the server on our last check. Among them: foresea_analyze_market, foresea_batch_forecast, foresea_batch_quotes, foresea_cancel_order, foresea_check_run, foresea_crypto_edge and 22 more. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Foresea Forecasting working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 221 ms. The bar chart above shows every period we have measured.

How do I connect Foresea Forecasting?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Foresea Forecasting need an API key?

No. Foresea Forecasting completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 28 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Foresea Forecasting?

It answers our handshake in 221 ms on average, which is faster than 64% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is Foresea Forecasting open source?

The code is open source: it is published under the MIT licence, written in Python, 0 stars on GitHub and 1 open issue. The licence covers the code in the repository, not the hosted service at foresea.ink, which runs on its operator's own terms.