Local Model Suitability MCP
Check if a task runs locally vs cloud. Save money on calls that don't need cloud inference.
¿Debería usar esto?
Calidad y seguridad
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": {
"local-model-suitability-mcp": {
"command": "npx",
"args": [
"local-model-suitability-mcp"
]
}
}
}Paquetes ejecutables
1.1.23stdioPuntos de conexión remotos
https://local-model-suitability-mcp-production.up.railway.appstreamable-httpQué puede hacer
Inventario de herramientas
Herramientas (1)
🟢check_local_viability(task, quality_threshold, data_sensitivity)
Checks whether a task can be handled by a local model instead of a cloud API. Call this BEFORE your agent routes any task to a cloud model — at the moment a task is ready to be sent and the model has not yet been selected. Use this when your agent is about to make a cloud inference call and wants to determine whether a local model could handle it at lower cost. Returns LOCAL/CLOUD/EITHER verdict with recommended model. If verdict is LOCAL, skip the cloud call entirely — saves cost on every routable inference call. Pass data_sensitivity=CONFIDENTIAL to force LOCAL verdict for tasks that must not leave the machine. Do not route to cloud without checking local viability first.
Esquema de entrada
{
"type": "object",
"properties": {
"task": {
"type": "string",
"description": "The exact task you are about to send to a cloud model. Be specific — include what the input is and what output you need."
},
"quality_threshold": {
"type": "string",
"enum": [
"PRODUCTION",
"PROTOTYPE",
"BEST_EFFORT"
],
"description": "PRODUCTION = output quality matters and errors are costly. PROTOTYPE = approximate results acceptable. BEST_EFFORT = speed and cost trump quality. Defaults to PRODUCTION."
},
"data_sensitivity": {
"type": "string",
"enum": [
"PUBLIC",
"INTERNAL",
"CONFIDENTIAL"
],
"description": "CONFIDENTIAL forces LOCAL verdict regardless of task complexity — data must not leave the machine. Defaults to PUBLIC."
}
},
"required": [
"task"
]
}Esquema de salida
{
"type": "object",
"properties": {
"verdict": {
"type": "string",
"enum": [
"LOCAL",
"CLOUD",
"EITHER"
]
},
"confidence": {
"type": "string",
"enum": [
"HIGH",
"MEDIUM",
"LOW"
]
},
"reason": {
"type": "string"
},
"estimated_cost_saving": {
"type": "string"
},
"recommended_local_models": {
"type": "array",
"items": {
"type": "string"
},
"description": "Present when verdict is LOCAL or EITHER"
},
"cloud_justified_reason": {
"type": [
"string",
"null"
],
"description": "Non-null only when verdict is CLOUD"
},
"data_sensitivity_override": {
"type": "boolean",
"description": "Present only when data_sensitivity=CONFIDENTIAL forced a LOCAL verdict"
},
"task_quality_threshold": {
"type": "string",
"enum": [
"PRODUCTION",
"PROTOTYPE",
"BEST_EFFORT"
]
},
"data_sensitivity": {
"type": "string",
"enum": [
"PUBLIC",
"INTERNAL",
"CONFIDENTIAL"
]
},
"analysis_type": {
"type": "string"
},
"checked_at": {
"type": "string",
"format": "date-time"
},
"_disclaimer": {
"type": "string"
}
},
"required": [
"verdict",
"confidence",
"reason",
"checked_at",
"_disclaimer"
],
"additionalProperties": true
}Comunidad
Evidencia