Forecasting MCP server
{
"mcpServers": {
"foresea-forecasting": {
"type": "http",
"url": "https://foresea.ink/mcp/"
}
}
}{
"mcpServers": {
"foresea-forecasting": {
"type": "http",
"url": "https://foresea.ink/mcp/"
}
}
}{
"mcpServers": {
"foresea-forecasting": {
"type": "http",
"url": "https://foresea.ink/mcp/"
}
}
}{
"servers": {
"foresea-forecasting": {
"type": "http",
"url": "https://foresea.ink/mcp/"
}
}
}{
"mcpServers": {
"foresea-forecasting": {
"type": "http",
"url": "https://foresea.ink/mcp/"
}
}
}file .mcp.json (in your project root)file claude_desktop_config.jsonfile ~/.cursor/mcp.jsonfile .vscode/mcp.jsonfile ~/.codeium/windsurf/mcp_config.jsonversion 1.0.0
What it does
Foresea is a prediction market intelligence platform that generates forecasts for binary and open-ended questions, identifies pricing discrepancies between model predictions and live markets (Polymarket and Kalshi), and provides an autonomous trading agent. It is for traders, researchers, and developers building on prediction market APIs.
- Get probability forecasts for events with supporting rationale and cited news evidence.
- Identify statistical edges by comparing Foresea model predictions to live Polymarket and Kalshi prices.
- Run autonomous multi-model paper trading tournaments and track performance metrics across different forecasting strategies.
Tools this server exposes
| Tool | Does |
|---|---|
| predict | Generate a probability forecast for a binary or open-ended question, with optional automatic news evidence retrieval and injection. |
| get_edges | Retrieve ranked pricing discrepancies between Foresea model forecasts and live market prices on Polymarket and Kalshi. |
| market_analysis | Analyze a specific market by comparing model probability, market probability, and historical performance metrics. |
Before you enable it
An MCP server runs with whatever access you give it. Start with a development account rather than production, and check which tools the server exposes before you let an agent call them unattended.