# Prediction Markets (Polymarket, PredictIt, Kalshi)

> Use this tool when you need to unify access to multiple prediction market platforms, such as Polymarket, PredictIt, and Kalshi, to fetch real-time market data, calculate odds, and retrieve event information. It solves problems of fragmented market research and trading analysis by providing a single interface for fetching and processing data from various platforms. The tool takes API requests as input and outputs calculated odds, contract pricing, and event data, making it ideal for market analysis, trading research, and building prediction market applications.

Canonical page: https://skillsregistry.net/skills/jamesanz-prediction-markets  
JSON: https://api.skillsregistry.net/v1/skills/jamesanz-prediction-markets

## Description

A prediction market server that provides real-time data from Polymarket, PredictIt, and Kalshi through three core functions: fetching Polymarket markets with calculated odds and keyword filtering, retrieving open PredictIt markets with contract pricing, and accessing Kalshi events data. Built with TypeScript and superagent for HTTP requests, it includes comprehensive type definitions for each platform's API responses and automatically filters for active markets only. The server calculates probability odds for Polymarket tokens and includes a postinstall setup script for Claude integration, making it useful for market analysis, trading research, and building prediction market applications that need unified access to multiple platforms.

## Trust

- **Trust score (0–1):** 0.94
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/jamesanz-prediction-markets)
- **Repository:** <https://github.com/jamesanz/prediction-market-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jamesanz-prediction-markets"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jamesanz-prediction-markets` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jamesanz-prediction-markets/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt