PredictionMarketsPicks Quant
Prediction-market quant tools — expected value, Kelly sizing, Bayesian updating, odds conversion, base-rate gaps, cross-platform arbitrage, and mispricing edge — for Kalshi and Polymarket contracts, exposed as a remote MCP server.
README
PredictionMarketsPicks MCP
A hosted Model Context Protocol server that gives AI agents institutional-grade quant tools for Kalshi and Polymarket prediction markets — expected value, Kelly sizing, Bayesian updating, probability conversion, cross-platform arbitrage, and live edge signals.
- Endpoint (Streamable HTTP):
https://predictionmarketspicks.com/api/mcp/mcp - Registry name:
com.predictionmarketspicks/quant(Model Context Protocol registry) - Docs / landing page: https://predictionmarketspicks.com/mcp
- Manifest:
server.json· also served athttps://predictionmarketspicks.com/.well-known/mcp/server.json - Type: Cloud service ☁️ · TypeScript 📇
This repo is the public home and documentation for the hosted server. The server is live — no install, no build. Point any MCP client at the endpoint above.
Tools
The free tier is a set of stateless quant calculators. Pro tools read PredictionMarketsPicks' live edge engines and require an API key.
| Tool | Tier | What it does |
|---|---|---|
calculate_ev |
Free | Expected-value edge on a contract from market price + your probability; returns edge % and a BUY / SELL / SKIP read. |
kelly_size |
Free | Optimal Kelly position size (full / half / quarter / eighth) from win probability, price, and bankroll, with a risk rating. |
bayes_update |
Free | Update a prior with one or more pieces of evidence via Bayes' theorem; returns the posterior and the per-step chain. |
convert_probability |
Free | Convert between implied probability, American odds, and decimal odds (American odds carry no commas). |
base_rate_gap |
Free | Compare a market price to the historical base rate for a class of events; returns the gap in points + sample-size quality. |
combo_edge |
Free | Grade a same-game multi-leg combo: EV %, fair vs offered odds, and a negative-correlation-trap flag. |
find_arbitrage |
Pro | Cross-platform price gaps between Kalshi and Polymarket on the same sports contract (NBA, NHL, MLB, World Cup). |
market_pulse |
Pro | US macro-health composite (0–100) and regime, plus six category scores. |
commodity_edge |
Pro | Largest model edge on a Kalshi weekly-silver or twice-daily bitcoin strike, as a trade ticket (side, price, criterion, edge, tier, ¼-Kelly). |
scan_mispricings |
Pro | Polymarket contracts trading away from the PMP model, with direction, edge in points, and quarter-Kelly sizing. |
All tool descriptions and outputs use prediction-market terminology (trader / position / contract / market analysis).
Connect
Claude Code
claude mcp add --transport http predictionmarketspicks https://predictionmarketspicks.com/api/mcp/mcp
Claude.ai, ChatGPT, or Cursor — add a custom connector / MCP server with the URL:
https://predictionmarketspicks.com/api/mcp/mcp
The free calculators work with no key. Pro tools require a PredictionMarketsPicks API key — see https://predictionmarketspicks.com/mcp.
About
Built by PredictionMarketsPicks — independent quant tools and edge analysis for Kalshi and Polymarket, published by The 7 Oracles.
License
MIT — see LICENSE. The hosted service and its live data are operated by PredictionMarketsPicks; this repository covers the server's public interface and documentation.
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。