Skip to main content
Glama
MCP Prediction Markets

MCP Prediction Markets

by huntbuilds

MCP Prediction Markets

Live prediction market intelligence for AI agents via the Model Context Protocol.

Tools

Tool

Description

search_prediction_markets

Search markets by keyword across Polymarket & Kalshi

get_trending_markets

Top markets by volume and activity

get_market_odds

Current odds and pricing for a specific market

find_arbitrage

Cross-platform price discrepancies (Kalshi vs Polymarket)

get_category_markets

Browse markets by category (crypto, politics, economics)

All data from free public APIs (Polymarket, Kalshi). No API keys required.

Related MCP server: Polymarket MCP Server

Install

pip install mcp-prediction-markets

Usage with Claude Desktop

Add to your Claude Desktop config (~/Library/Application Support/Claude/claude_desktop_config.json):

{
  "mcpServers": {
    "prediction-markets": {
      "command": "mcp-prediction-markets"
    }
  }
}

Then ask Claude things like:

  • "Search for Bitcoin prediction markets"

  • "What are the trending markets on Polymarket?"

  • "Find arbitrage opportunities between Kalshi and Polymarket"

  • "What are the odds on the Fed cutting rates?"

License

MIT

Available Tools

5 tools
find_arbitrageA

Find cross-platform arbitrage between Polymarket and Kalshi.

Scans equivalent markets on both platforms for price discrepancies. When the combined cost of opposing positions < $1.00, the difference is guaranteed profit regardless of outcome.

Real arbs are typically 1-5 cents and close within seconds/minutes. Larger spreads (>20 cents) usually indicate markets are NOT equivalent.

Args: min_spread_cents: Minimum spread to report in cents (default 2.0)

Returns: JSON with arbitrage opportunities, matched pairs, and spread analysis.

Inputs: min_spread_cents. Returns: result

get_category_marketsA

Browse prediction markets by category.

Categories: crypto, economics, politics, climate, sports, entertainment, geopolitics, tech, other.

Args: category: Market category (crypto, economics, politics, climate, sports, entertainment, geopolitics, tech, other) platform: "both", "polymarket", or "kalshi" (default "both") limit: Max results (default 20, max 50)

Returns: JSON with markets in the specified category, sorted by volume.

Inputs: category, platform, limit. Returns: result

get_market_oddsB

Get detailed current odds and pricing for a specific prediction market.

Provides YES/NO prices, implied probability, volume, and market metadata. Use the market_id from search_prediction_markets or get_trending_markets.

Args: market_id: The market identifier (Kalshi ticker like "KXBTC-26MAR15-B100000" or Polymarket condition_id) platform: "polymarket" or "kalshi"

Returns: JSON with detailed market odds, pricing, and metadata.

Inputs: market_id (required), platform. Returns: result

search_prediction_marketsA

Search prediction markets across Polymarket and Kalshi by keyword.

Find markets about any topic: crypto prices, elections, economic indicators, geopolitics, entertainment, tech, sports, and more. Returns current odds (YES/NO prices), volume, and direct links.

Args: query: Search keywords (e.g., "bitcoin 100k", "trump", "fed rate cut", "gta vi") platform: "both", "polymarket", or "kalshi" (default "both") limit: Maximum results to return (default 15, max 30)

Returns: JSON with matching markets, current odds, and links.

Inputs: query (required), platform, limit. Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.1/5.0

    Scored across 5 tools

    Disambiguation5/5

    Each tool has a distinct purpose: find_arbitrage detects cross-platform arbitrage, get_category_markets browses by category, get_market_odds fetches specific odds, get_trending_markets shows trending markets, and search_prediction_markets searches by keyword. No overlap.

    Naming Consistency5/5

    All tool names follow a consistent verb_noun pattern in snake_case. Most use 'get_' prefix, while 'find_arbitrage' uses 'find_' which is still a clear verb_noun construction. Naming is predictable and uniform.

    Tool Count5/5

    Five tools cover the essential information retrieval needs of a prediction markets server: discovering, searching, browsing, and checking odds, plus a unique arbitrage detection tool. The count is well-scoped and not excessive.

    Completeness4/5

    The tool set covers major read operations: search, browse, trending, odds, and arbitrage. However, it lacks tools for historical data, market analysis, or user portfolio management, which are reasonable extensions for a more complete prediction markets server.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      Aggregates prediction market data from 5 major platforms (Manifold, Polymarket, Metaculus, PredictIt, Kalshi), enabling users to search markets, compare odds across platforms, detect arbitrage opportunities, and track predictions through natural language.
      8
      5
      MIT
    • A
      license
      B
      quality
      Not graded
      maintenance
      Enables AI agents to interact with the Polymarket prediction market platform to discover markets, analyze real-time pricing, and monitor public portfolio data. It provides comprehensive access to market analytics, implied probabilities, and order books through the Model Context Protocol.
      59
      32 npm
      -
    • A
      license
      A
      quality
      C
      maintenance
      Enables AI agents to discover and analyze prediction markets, execute trades, and manage positions on Polymarket via the Model Context Protocol.
      7
      86 npm
      22
      MIT