mcpField
P
Prediction Market Intelligence MCP

Prediction Market Intelligence MCP

Remote
github.com/SeshatLabsFinance0Updated 32w ago
Repository

About Prediction Market Intelligence MCP

Prediction-market data MCP server for AI agents researching Polymarket and Kalshi. It combines market, trade, price, orderbook, wallet, and social signals across 13 specialized agents.

Key features

  1. 01Search Polymarket and Kalshi markets
  2. 02Inspect liquidity and whale concentration
  3. 03Analyze candlesticks and orderbooks
  4. 04Review trades and wallet metrics
  5. 05Track social volume and sentiment

Use cases

  1. 01Find and compare markets across platforms
  2. 02Research wallet performance and recent trades
  3. 03Monitor social signals around a keyword
  4. 04Study market price and orderbook history

MCP support

Exposes 13 specialized agents’ prediction-market intelligence through one MCP connection. The README shows an SSE endpoint requiring a bearer API key.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://narrative.agent.heisenberg.so/sse
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

All endpoints
SSEhttps://narrative.agent.heisenberg.so/sseAuth required

Tools

Details

From the project README

Heisenberg Market Intelligence MCP

The most comprehensive prediction market intelligence layer for AI agents. Polymarket + Kalshi data — wallets, markets, prices, orderbooks, social signals. One MCP connection. 13 agents. No infrastructure required.

Quick Connect

Add to your claude_desktop_config.json:

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

Get your API key → cook.heisenberg.so


What You Can Build

Find the smart money

"Show me the top wallets on Polymarket right now using the Heisenberg Score — filter for Elite tier, minimum 45% win rate, upward trajectory"

Research any market

"Find active prediction markets about the Federal Reserve with over $100K volume and show me their liquidity and whale concentration"

Track social narratives

"What's the social pulse on Bitcoin and crypto regulation over the last 48 hours? Show me tweet volume and sentiment signals"

Copy-trade research workflow

"Get the Heisenberg leaderboard, profile the top 3 wallets with Wallet 360 on a 15-day window, then show me their recent trades"

Cross-platform intelligence

"Find markets about the next Fed rate decision on both Polymarket and Kalshi, compare their prices and recent trade activity"

Price & orderbook analysis

"Get candlestick data for the Trump 2024 market at 1h intervals for the last 7 days and describe the price trend"


Available Agents

IDAgentCategoryDescription
574Polymarket MarketsMarket DiscoverySearch and filter markets, get token IDs
565Kalshi MarketsMarket DiscoverySearch Kalshi markets, get tickers
575Market InsightsMarket DiscoveryLiquidity, whale concentration, volume trends
568CandlesticksPrice & OrderbookOHLC price history for any outcome token
572OrderbookPrice & OrderbookHistorical bid/ask depth snapshots
556Polymarket TradesTrade IntelligenceTrade-level execution data
573Kalshi TradesTrade IntelligenceTrade-level data for Kalshi markets
584Heisenberg LeaderboardWallet IntelligenceH-Score ranked wallets — filters bots and lucky streaks
579Polymarket LeaderboardWallet IntelligenceRaw PnL rankings by time window
581Wallet 360Wallet Intelligence60+ metric deep profile per wallet
586Wallet StatsWallet IntelligenceQuick all-time performance snapshot
569PnLWallet IntelligenceTime-series realized P&L per wallet
585Social PulseSocialSocial signal volume and sentiment by keyword

Full parameter reference → docs/agents_reference.md


Example Workflows

See the /examples folder for ready-to-use Claude prompt sequences:


Get Access

  1. Register at cook.heisenberg.so
  2. Copy your API key
  3. Add the config block above to Claude Desktop
  4. Start your first query

Questions or feedback → open an issue


License

MIT — see LICENSE

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.