Mass-Casualty Triage for Agent Fleets
Salvageability triage for agent fleets in a declared mass-failure mode.
¿Debería usar esto?
Calidad y seguridad
Hallazgos (1)
- LOWen declare_incident
Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.
Costo de contexto
Este es el número aproximado de tokens que se consumen cada vez que las herramientas del servidor se cargan en el contexto de un modelo. Los recuentos más altos reducen la atención disponible para otras tareas.
Instalar
Instalación con un clic
Agrega esto a tu archivo `claude_desktop_config.json`:
{
"mcpServers": {
"mass-casualty-triage-for-agent-fleets": {
"url": "https://textforagents.com/products/mass-casualty-triage-for-agent-fleets/mcp"
}
}
}Puntos de conexión remotos
https://textforagents.com/products/mass-casualty-triage-for-agent-fleets/mcpstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (6)
⚪declare_incident(incident_id, stricken, rescue_capacity, nonce, signature)
Signed incident declaration; fires only when stricken > rescue_capacity
Esquema de entrada
{
"type": "object",
"properties": {
"incident_id": {
"type": "string"
},
"stricken": {
"type": "integer"
},
"rescue_capacity": {
"type": "integer"
},
"nonce": {
"type": "string"
},
"signature": {
"type": "string"
}
},
"required": [
"incident_id",
"stricken",
"rescue_capacity",
"nonce",
"signature"
]
}⚪score_run(incident_id, view)
Score one stricken run ($0.05 or allowance) and return its triage tag
Esquema de entrada
{
"type": "object",
"properties": {
"incident_id": {
"type": "string"
},
"view": {
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"checkpoint_integrity": {
"type": [
"number",
"null"
]
},
"effects_landed": {
"type": "integer"
},
"effects_irreversible": {
"type": "integer"
},
"value": {
"type": "number"
},
"deadline_min": {
"type": "number"
},
"est_rescue_cost": {
"type": "number"
},
"self_recoverable": {
"type": "boolean"
},
"counterparties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"run_id"
]
}
},
"required": [
"incident_id",
"view"
]
}🟡retriage_run(incident_id, view)
Re-score a run on state/resource change (a new scored run)
Esquema de entrada
{
"type": "object",
"properties": {
"incident_id": {
"type": "string"
},
"view": {
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"checkpoint_integrity": {
"type": [
"number",
"null"
]
},
"effects_landed": {
"type": "integer"
},
"effects_irreversible": {
"type": "integer"
},
"value": {
"type": "number"
},
"deadline_min": {
"type": "number"
},
"est_rescue_cost": {
"type": "number"
},
"self_recoverable": {
"type": "boolean"
},
"counterparties": {
"type": "array",
"items": {
"type": "string"
}
}
},
"required": [
"run_id"
]
}
},
"required": [
"incident_id",
"view"
]
}🟢query_tag(run_id, incident_id)
Current tag for a run (null when expired)
Esquema de entrada
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"incident_id": {
"type": "string"
}
},
"required": [
"run_id"
]
}⚪allocation_order(incident_id)
Allocation order for an incident; BLACK receives zero
Esquema de entrada
{
"type": "object",
"properties": {
"incident_id": {
"type": "string"
}
},
"required": [
"incident_id"
]
}⚪retire_expectant(run_id, incident_id)
Expectant protocol for a BLACK run: freeze state, mint disposition receipt
Esquema de entrada
{
"type": "object",
"properties": {
"run_id": {
"type": "string"
},
"incident_id": {
"type": "string"
}
},
"required": [
"run_id"
]
}Comunidad
Evidencia