Polymarket vs Kalshi MCP Server
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Polymarket vs Kalshi MCP Server
Give your AI agent the same prediction market on Polymarket and Kalshi, matched and verified, with both prices, the gap between them, the pre-fee edge, alerts when a gap opens, and 30-day price history.
10,000+ verified pairs across elections, politics, economics, crypto and sports
Sports line by line: game winners, spreads and totals in 100+ leagues (NFL, NBA, NHL, college, soccer, esports)
Gap alerts: pairs whose gap just opened, newest first
Refreshed every hour
Hosted remote MCP server (Streamable HTTP) running on Apify. Nothing to install.
Connect
Server URL:
https://mcp.apify.com?tools=forgedata/prediction-markets-apiClaude: add the URL as a custom connector, then sign in to Apify when asked. A free Apify account works.
Cursor, VS Code, Windsurf and other clients:
{
"mcpServers": {
"polymarket-kalshi": {
"url": "https://mcp.apify.com?tools=forgedata/prediction-markets-api"
}
}
}Prefer a token over sign-in? Add "headers": { "Authorization": "Bearer YOUR_APIFY_TOKEN" }.
Related MCP server: parsec-mcp
Things to ask your agent
"Find markets that are on both Polymarket and Kalshi with a gap over 5 cents that traded today."
"Which NBA spreads tonight differ most between Polymarket and Kalshi?"
"Show me gap alerts from the last hour, politics only."
"What are Polymarket and Kalshi pricing for control of the Senate?"
How matching works
Questions are matched on their wording with strict checks: numbers, years and dates must agree, words like "not" or "before" or a party name must appear on both sides, and every named person or place must appear on both sides. Sports games are matched by league, date and both teams, then each winner, spread and total line is paired with the exact same line on the other platform. Gaps are only reported when both sides show a live quote, so empty order books do not show up as fake opportunities.
Pricing
Pay per result through your Apify account: $3.00 per 1,000 results, lower on Apify's paid tiers. Apify's free plan includes monthly usage credit.
Also available as a REST API
Notes
Data comes from the public market data both platforms publish. Not affiliated with Polymarket or Kalshi. Resolution rules can differ in the details between platforms, so read both before trading. Information only, not financial advice.
Built by Data Forge. MIT license.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Cross-venue prediction market odds (Polymarket, Kalshi, PredictIt, Manifold) with arbitrage signals
Live prediction markets: Polymarket + Kalshi prices, odds, order books. Pay-per-call USDC, no key.
Matched Kalshi and Polymarket markets across sports, crypto, weather, and economics over MCP.
Sports prediction markets for AI agents — live prices, quotes, orders, and positions.
Related MCP Servers
- AlicenseAqualityDmaintenanceAggregates 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.85MIT
- FlicenseNot gradedqualityDmaintenanceTrade and monitor prediction markets across Polymarket, Kalshi, Opinion, Limitless, and PredictFun from any AI agent. Unified real-time data, live orderbook streaming, and order execution — one API key, one interface, five exchanges.-
- AlicenseAqualityDmaintenancePrediction market probability oracle for AI agents. 26 tools across 500+ live markets from Kalshi and Polymarket. Cross-source arbitrage detection, structured TPF signals, Kelly Criterion sizing, agent performance tracking, and webhook alerts.986 npm1MIT

meridian-edge-mcpofficial
AlicenseAqualityDmaintenanceProvides AI assistants with real-time prediction market consensus data, including probabilities, opportunities, signals, and settlements.5MIT