get_calibration
Retrieve signal accuracy metrics including Brier scores, hit rates, and total signals to assess prediction calibration for trading decisions.
Instructions
Get signal accuracy and calibration metrics — Brier score, hit rates, total signals.
Args: category: Filter by category (e.g. "crypto", "politics") or "" for all. period: Time period: "7d", "30d", "90d", or "all". mode: Trading mode: "shadow" or "live".
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| category | No | ||
| period | No | all | |
| mode | No | shadow |
Implementation Reference
- src/rekko_mcp/server.py:180-193 (handler)The get_calibration function is registered as an MCP tool and handles the retrieval of signal accuracy and calibration metrics from the Rekko API.
async def get_calibration( category: str = "", period: str = "all", mode: str = "shadow" ) -> str: """Get signal accuracy and calibration metrics — Brier score, hit rates, total signals. Args: category: Filter by category (e.g. "crypto", "politics") or "" for all. period: Time period: "7d", "30d", "90d", or "all". mode: Trading mode: "shadow" or "live". """ params: dict = {"period": period, "mode": mode} if category: params["category"] = category return await _request("GET", "/v1/calibration", params=params)