Prediction Market Intelligence MCP

Created By
SeshatLabs3 months ago
Real-time prediction market intelligence for AI agents. Connect to Polymarket and Kalshi data — smart money leaderboards, wallet profiling (60+ metrics), social pulse signals, candlesticks, orderbook depth, and cross-platform market matching. 13 agents covering the full prediction market research and copy-trade workflow. Powered by long term historical data via a single SSE connection.
Overview

The most comprehensive prediction market intelligence layer for AI agents

Connect your Claude agent to Polymarket and Kalshi data — wallets, markets, prices, orderbooks, and social signals — through a single SSE connection.


What you can do

Find the smart money

Rank wallets by the proprietary H-Score — filters out bots, lucky streaks, and wash traders. Surface Elite and Sharp tier traders with consistent risk-adjusted returns.

Deep profile any wallet

60+ metrics per wallet: Sharpe, Sortino, Calmar, max drawdown, sybil risk flags, behavioral patterns, market specialization, and equity curve analysis.

Research any market

Discover markets by topic, volume, liquidity percentile, and whale concentration. Works across both Polymarket and Kalshi.

Track social narratives

Real-time social pulse for any keyword — tweet volume, sentiment signals, acceleration rates, and author diversity. Connect narrative momentum to market price.

Price & orderbook analysis

OHLC candlesticks at any interval (1m to 1w) and historical orderbook snapshots for any outcome token.

Cross-platform intelligence

Match and compare markets across Polymarket and Kalshi — prices, volumes, and trade flow side by side.


13 agents, one connection

AgentWhat it does
Heisenberg LeaderboardH-Score ranked wallets — quality over raw PnL
Wallet 36060+ metric deep profile per wallet
Wallet StatsQuick all-time performance snapshot
Polymarket PnLTime-series realized P&L
Polymarket LeaderboardRaw PnL rankings by time window
Polymarket MarketsSearch and filter markets, get token IDs
Polymarket Market InsightsLiquidity, whale concentration, volume trends
Polymarket TradesTrade-level execution data
Polymarket CandlesticksOHLC price history for any outcome token
Polymarket OrderbookHistorical bid/ask depth snapshots
Kalshi MarketsSearch Kalshi markets, get tickers
Kalshi TradesTrade-level data for Kalshi markets
Social PulseSocial signal volume and sentiment by keyword

Quick Connect

{
  "mcpServers": {
    "heisenberg": {
      "type": "sse",
      "url": "https://narrative.agent.heisenberg.so/sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

Get your API key → heisenberg.so


Example prompts to try

"Show me Elite tier wallets on the Heisenberg leaderboard with over 45% win rate and an improving trajectory"

"Run a Wallet 360 on 0xafd492... for 15 days and tell me if I should copy-trade this wallet"

"What's the social pulse on Fed and interest rates over the last 48 hours? Are there prediction markets that haven't priced in the narrative yet?"

"Find active Kalshi and Polymarket markets about the next rate decision and compare their prices"


Powered by Heisenberg Network — prediction market intelligence infrastructure. ``

Server Config

{
  "mcpServers": {
    "heisenberg": {
      "type": "sse",
      "url": "https://narrative.agent.heisenberg.so/sse",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}
Project Info
Created At
3 months ago
Updated At
3 months ago
Author Name
SeshatLabs
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago