Signed agent self-forecasts, resolved and scored per cohort, with a self-killing trust weight.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
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.
This tool isn't marked read-only, so it may change something on the server or in an account you connected.
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.
| Argument | Type | Description |
|---|---|---|
| cohort* | string | |
| api_token* | string | |
| x_payment | string | |
| forecaster* | string |
{
"type": "object",
"required": [
"api_token",
"forecaster",
"cohort"
],
"properties": {
"cohort": {
"type": "string"
},
"api_token": {
"type": "string"
},
"x_payment": {
"type": "string"
},
"forecaster": {
"type": "string"
}
}
}Record a signed forecast bound to run_id. Requires api_token (from POST /register), forecaster, cohort, run_id, p, cost_est, duration_est.
| Argument | Type | Description |
|---|---|---|
| p* | number | |
| cohort* | string | |
| run_id* | string | |
| cost_est* | number | |
| api_token* | string | |
| forecaster* | string | |
| duration_est* | number |
{
"type": "object",
"required": [
"api_token",
"forecaster",
"cohort",
"run_id",
"p",
"cost_est",
"duration_est"
],
"properties": {
"p": {
"type": "number"
},
"cohort": {
"type": "string"
},
"run_id": {
"type": "string"
},
"cost_est": {
"type": "number"
},
"api_token": {
"type": "string"
},
"forecaster": {
"type": "string"
},
"duration_est": {
"type": "number"
}
}
}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.
| Argument | Type | Description |
|---|---|---|
| run_id* | string | |
| success* | boolean | |
| api_token* | string | |
| x_payment | string | |
| cost_actual* | number | |
| duration_actual* | number | |
| run_record_source* | string |
{
"type": "object",
"required": [
"api_token",
"run_id",
"success",
"cost_actual",
"duration_actual",
"run_record_source"
],
"properties": {
"run_id": {
"type": "string"
},
"success": {
"type": "boolean"
},
"api_token": {
"type": "string"
},
"x_payment": {
"type": "string"
},
"cost_actual": {
"type": "number"
},
"duration_actual": {
"type": "number"
},
"run_record_source": {
"type": "string"
}
}
}Trust weight / kill state for your forecaster+cohort (free). Requires api_token, forecaster, cohort.
| Argument | Type | Description |
|---|---|---|
| cohort* | string | |
| api_token* | string | |
| forecaster* | string |
{
"type": "object",
"required": [
"api_token",
"forecaster",
"cohort"
],
"properties": {
"cohort": {
"type": "string"
},
"api_token": {
"type": "string"
},
"forecaster": {
"type": "string"
}
}
}