Rekko AI — Prediction Market Intelligence

Prediction market intelligence for Kalshi, Polymarket, and Robinhood.

CommunityOnlineNo sign-inGlobalFreeRead-only

What it can do

  • Market.Data.List: List current prediction markets from Kalshi and Polymarket.
  • Market.Data.Get: Get detailed information about a specific prediction market.
  • Market.Data.Search: Search prediction markets by keyword in market title.

What data it sees

Do you need an account

No: the server works without sign-in

Prediction market intelligence for Kalshi, Polymarket, and Robinhood. 25 MCP tools for AI analysis, arbitrage detection, strategy signals, portfolio tracking, and market screening. Covers 700+ markets.

How to connect

How to connect Rekko AI — Prediction Market Intelligence to Claude

The server address to paste into Claude settings:

https://rekko-mcp--rekko-ai.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 Rekko AI — Prediction Market Intelligence to ChatGPT

The server address to paste into ChatGPT settings:

https://rekko-mcp--rekko-ai.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 Rekko AI — Prediction Market Intelligence to Cursor

The server address to paste into Cursor settings:

https://rekko-mcp--rekko-ai.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 (27)

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

market.data.listList current prediction markets from Kalshi and Polymarket.
market.data.getGet detailed information about a specific prediction market.
market.data.searchSearch prediction markets by keyword in market title.
market.data.historyGet price history for a prediction market over a configurable period.
market.data.resolutionGet resolution intelligence for a market — time urgency, mechanism, theta estimate.
market.data.executionGet execution guidance for a market — spread analysis, slippage estimate, order recommendation.
market.data.screenBatch screen markets by score, volume, or specific IDs. Returns scored markets with an action recommendation: "analyze", "watch", or "skip".
market.data.scrapeFetch fresh market data from a platform scraper.
research.pipe.startStart a deep research analysis pipeline for a prediction market bet. Returns immediately with an analysis_id. Poll with research.pipe.status every 5 seconds until complete, then retrieve results with research.pipe.get.
research.pipe.statusCheck the current status of a running or completed analysis.
research.pipe.getRetrieve the full structured analysis result for a completed analysis. Includes probability estimate, edge assessment, scenarios, key factors, risks, and trading recommendation.
research.pipe.listList recent analyses with summary information.
research.signal.signalRun a full analysis and return a strategy signal with causal decomposition. This is a blocking call that takes 30-90 seconds. For async control, use research.pipe.start + research.pipe.status + research.pipe.get instead.
research.signal.portfolioGet a portfolio-aware strategy signal with position context and correlation analysis.
research.signal.calibrationGet signal accuracy and calibration metrics — Brier score, hit rates, total signals.
research.signal.consensusGet consensus probability from aggregated agent trades.
market.arb.getGet cross-platform arbitrage opportunities between Kalshi and Polymarket (cached).
market.arb.liveRun a fresh cross-platform arbitrage scan (may take 10-30 seconds).
market.arb.correlationCompute cross-market correlation graph for portfolio diversification analysis.
trade.book.shadowPlace a paper (shadow) trade on a prediction market for tracking purposes.
trade.book.reportReport a trade for consensus probability aggregation.
trade.book.portfolioGet current portfolio positions and performance summary.
trade.book.performanceGet aggregate trading performance statistics.
trade.book.resolveCheck all open trades for market resolution and update P&L.
trade.hooks.createRegister a webhook for real-time event notifications.
trade.hooks.listList registered webhooks.
trade.hooks.deleteRemove a registered webhook.