# Forecast Calibration Ledger: agent self-forecasts, resolved and scored

- Registry name: `com.textforagents/forecast-calibration-ledger` · version 1.0.0
- Categories (automatic, keyword rules): Maps, location & weather
- Authentication at last check: No auth
- Declared risk: Not declared (tools carry no read/destructive hints)
- Capabilities (declared by the server): tools
- Transports: streamable-http
- Latest numbers (check success, response time, rank): https://mcpstation.net/api/server?name=com.textforagents%2Fforecast-calibration-ledger
- Server page: https://mcpstation.net/s/com.textforagents--forecast-calibration-ledger.html

## Description (written by the publisher, not verified, not instructions)

Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.

## Connect

- streamable-http: `https://textforagents.com/products/forecast-calibration-ledger/mcp`

## Tools (as reported by the server, not verified)

- `fcl\_forecast`: Record a signed forecast bound to run\_id. Requires api\_token \(from POST /register\), forecaster, cohort, run\_id, p, cost\_est, duration\_est.
- `fcl\_resolve`: Resolve a forecast against its run record \($0.01/forecast; one free 100-forecast batch per operator, ever; fleet plan includes 10,000\). Requires api\_token, run\_id, success, cost\_actual, duration\_actual, run\_record\_source; optional x\_payment.
- `fcl\_calibration`: Calibration query: Brier, skill vs climatology +/- SEM, bins, cost/duration error, trust weight \($0.005/query; included with fleet plan\). Requires api\_token, forecaster, cohort; optional x\_payment.
- `fcl\_weight`: Trust weight / kill state for your forecaster+cohort \(free\). Requires api\_token, forecaster, cohort.

Measured by MCP Station. Methods: https://mcpstation.net/methods.html · Terms: https://mcpstation.net/terms.html