prediction-markets

prediction-markets

Provides AI agents with real-time prediction market odds from Polymarket and Kalshi, enabling them to browse active markets, retrieve detailed probabilities and trading data, and discover trending markets via x402 micropayments.

Category
访问服务器

README

Prediction Markets API

MCP Server x402 License: MIT

Real-time prediction market odds from Polymarket and Kalshi. Active markets, probabilities, volume, categories. The betting intelligence layer agents need for event forecasting. Pay-per-call via x402 (USDC on Base L2) -- no API key, no signup, no rate-limit wall.

Part of the klymax402 marketplace -- 100 x402 micropayment APIs for AI agents, one wallet, USDC on Base.

Quickstart -- MCP

Add to your MCP client config (Claude Desktop, Cursor, ElizaOS, etc.):

{
  "mcpServers": {
    "prediction-markets": {
      "url": "https://prediction-markets.api.klymax402.com/mcp"
    }
  }
}

Quickstart -- HTTP (x402)

curl -X POST "https://prediction-markets.api.klymax402.com/api/markets" \
  -H "Content-Type: application/json" \
  -d '{}'
# -> 402 Payment Required, with an x402 payment challenge in the response body

Any x402-aware client (@x402/fetch, x402-agent-tools, ATXP) handles the 402 -> sign -> retry cycle automatically.

Tools

Tool Method Path Price Description
prediction_list_markets POST /api/markets $0.012 List active prediction markets from Polymarket and Kalshi with current odds, volume, and categories. Filter by topic, platform, and sort by volume, newest, or closing soon.
prediction_get_market_odds POST /api/odds $0.012 Get detailed odds and trading data for a specific prediction market by ID or search query. Searches both Polymarket and Kalshi.
prediction_trending_markets POST /api/trending $0.008 Top trending prediction markets from Polymarket and Kalshi ranked by volume and engagement.

prediction_list_markets

Use this when you need to browse active prediction markets or find betting odds on real-world events. Returns a list of active markets from Polymarket and Kalshi with current probabilities, trading volume, and metadata.

Parameters

Name Type Required Description
category string no Filter markets by topic category. Omit for all categories.
limit number no Number of markets to return (1-50). Default: 20.
sort string no Sort order. 'volume' = highest traded, 'newest' = recently created, 'closing_soon' = ending soonest. Default: volume.
source string no Filter by platform. Omit to get markets from both Polymarket and Kalshi.

Returns

  • question -- the prediction market question (e.g. "Will Bitcoin reach $100k by December 2026?")
  • outcomePrices -- probability for each outcome as decimal (0.65 = 65% chance YES)
  • volume -- total trading volume in USD
  • liquidity -- current available liquidity in USD
  • endDate -- when the market resolves
  • category -- topic category (politics, crypto, sports, science, culture)
  • active -- whether the market is currently trading
  • source -- data source -- "polymarket" or "kalshi"

Example response:

{ markets: [{ question: "Will Trump win 2028?", outcomePrices: { "Yes": 0.42, "No": 0.58 }, volume: 15420000, liquidity: 890000, endDate: "2028-11-06", category: "politics", source: "polymarket" }] }

Not for: crypto price data (use token_get_price), crypto news (use crypto_get_news), stock prices (use stock_get_quote), DeFi yields (use defi_find_best_yields), Hyperliquid perp data (use hyperliquid_get_market_data).

prediction_get_market_odds

Use this when you need detailed odds, probabilities, and trading data for a specific prediction market. Searches both Polymarket and Kalshi to find the best match by market ID or question text.

Parameters

Name Type Required Description
marketId string no Polymarket condition ID or Kalshi ticker. Use this if you already know the market ID.
query string no Search query to find a market by question text (e.g. 'bitcoin 100k', 'trump election'). Used when marketId is not known.

Returns

  • question -- the full prediction market question text
  • outcomes -- array of possible outcomes with their current probabilities
  • outcomePrices -- decimal probabilities per outcome (0.72 = 72% implied probability)
  • volume -- total all-time trading volume in USD
  • volume24h -- trading volume in the last 24 hours
  • liquidity -- current depth of the order book in USD
  • endDate -- resolution date of the market
  • description -- detailed market description and resolution criteria
  • active -- whether the market is currently open for trading
  • source -- which platform the market is from -- "polymarket" or "kalshi"

Example response:

{ question: "Will ETH flip BTC by 2027?", outcomes: ["Yes", "No"], outcomePrices: { "Yes": 0.08, "No": 0.92 }, volume: 2340000, volume24h: 45000, liquidity: 120000, endDate: "2027-12-31", active: true, source: "polymarket" }

Not for: crypto price data (use token_get_price), crypto news (use crypto_get_news), stock prices (use stock_get_quote), DeFi yields (use defi_find_best_yields), Hyperliquid perp data (use hyperliquid_get_market_data).

prediction_trending_markets

Use this when you need to see what prediction markets are trending right now. Returns the hottest markets from both Polymarket and Kalshi ranked by recent trading volume and activity.

Parameters

Name Type Required Description
limit number no Number of trending markets to return (1-30). Default: 10.
source string no Filter by platform. Omit to get trending markets from both Polymarket and Kalshi.

Returns

  • question -- the market question
  • probability -- current implied probability for the leading outcome (decimal)
  • volume24h -- trading volume in the last 24 hours in USD
  • totalVolume -- all-time trading volume in USD
  • priceChange24h -- change in probability over the last 24 hours (e.g. +0.05 = probability rose 5%)
  • category -- topic category
  • endDate -- when the market resolves
  • source -- data source -- "polymarket" or "kalshi"

Example response:

{ trending: [{ question: "Will Fed cut rates in July 2026?", probability: 0.73, volume24h: 890000, totalVolume: 12500000, priceChange24h: 0.08, category: "politics", endDate: "2026-07-31", source: "polymarket" }] }

Not for: crypto price data (use token_get_price), crypto news (use crypto_get_news), stock prices (use stock_get_quote), DeFi yields (use defi_find_best_yields), Hyperliquid perp data (use hyperliquid_get_market_data).

Example agent prompts

  • "Browse active prediction markets or find betting odds on real-world events"
  • "Detailed odds, probabilities, and trading data for a specific prediction market"
  • "See what prediction markets are trending right now"

Payment

  • Protocol: x402 -- HTTP-native pay-per-call, no signup, no API key
  • Network: Base L2 (eip155:8453)
  • Asset: USDC
  • Facilitator: Coinbase CDP (primary), PayAI (fallback)
  • Also reachable via ATXP (OAuth-wrapped x402, RFC 9728 protected-resource metadata)

Part of klymax402

100 x402 micropayment APIs for AI agents -- one wallet, USDC on Base, zero signup.

  • Catalog: https://klymax402.com/llms.txt
  • Full API reference: https://klymax402.com/llms-full.txt
  • Live stats: https://klymax402.com/stats

License

MIT

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选
mcp-server-qdrant

mcp-server-qdrant

这个仓库展示了如何为向量搜索引擎 Qdrant 创建一个 MCP (Managed Control Plane) 服务器的示例。

官方
精选