Forecast Calibration Ledger: agent self-forecasts, resolved and scored
Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.
使うべきか
品質と安全性
検出事項(1)
- LOWfcl_weight 内
ツール定義とプロトコルへの準拠に関する自動分析に基づいています。
コンテキストコスト
これは、サーバーのツールがモデルのコンテキストに読み込まれるたびに消費されるおおよそのトークン数です。数が多いほど、ほかのタスクに使える注意が減ります。
インストール
ワンクリックインストール
これを `claude_desktop_config.json` ファイルに追加してください:
{
"mcpServers": {
"forecast-calibration-ledger": {
"url": "https://textforagents.com/products/forecast-calibration-ledger/mcp"
}
}
}リモートエンドポイント
https://textforagents.com/products/forecast-calibration-ledger/mcpstreamable-httpできること
ツール一覧
ツール(4)
🟡fcl_forecast(api_token, forecaster, cohort, run_id, p, ...)
Record a signed forecast bound to run_id. Requires api_token (from POST /register), forecaster, cohort, run_id, p, cost_est, duration_est.
入力スキーマ
{
"type": "object",
"properties": {
"api_token": {
"type": "string"
},
"forecaster": {
"type": "string"
},
"cohort": {
"type": "string"
},
"run_id": {
"type": "string"
},
"p": {
"type": "number"
},
"cost_est": {
"type": "number"
},
"duration_est": {
"type": "number"
}
},
"required": [
"api_token",
"forecaster",
"cohort",
"run_id",
"p",
"cost_est",
"duration_est"
]
}⚪fcl_resolve(api_token, run_id, success, cost_actual, duration_actual, ...)
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.
入力スキーマ
{
"type": "object",
"properties": {
"api_token": {
"type": "string"
},
"run_id": {
"type": "string"
},
"success": {
"type": "boolean"
},
"cost_actual": {
"type": "number"
},
"duration_actual": {
"type": "number"
},
"run_record_source": {
"type": "string"
},
"x_payment": {
"type": "string"
}
},
"required": [
"api_token",
"run_id",
"success",
"cost_actual",
"duration_actual",
"run_record_source"
]
}⚪fcl_calibration(api_token, forecaster, cohort, x_payment)
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.
入力スキーマ
{
"type": "object",
"properties": {
"api_token": {
"type": "string"
},
"forecaster": {
"type": "string"
},
"cohort": {
"type": "string"
},
"x_payment": {
"type": "string"
}
},
"required": [
"api_token",
"forecaster",
"cohort"
]
}⚪fcl_weight(api_token, forecaster, cohort)
Trust weight / kill state for your forecaster+cohort (free). Requires api_token, forecaster, cohort.
入力スキーマ
{
"type": "object",
"properties": {
"api_token": {
"type": "string"
},
"forecaster": {
"type": "string"
},
"cohort": {
"type": "string"
}
},
"required": [
"api_token",
"forecaster",
"cohort"
]
}コミュニティ
エビデンス