LLM Audit

Measure whether AI assistants actually recommend a brand, from measured answers.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
100%
Integridad del esquema
100%
Calidad de los nombres
100%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Basado en el análisis automatizado de las definiciones de herramientas y el cumplimiento del protocolo.

Costo de contexto

~558Tokens (definiciones de herramientas)
~1.8 KBTamaño de respuesta típico
Impacto mínimo en la atención (0.44% del contexto de 128k)

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": {
    "llmaudit": {
      "command": "npx",
      "args": [
        "llmaudit-mcp"
      ]
    }
  }
}

Paquetes ejecutables

npmllmaudit-mcp0.1.0stdio

Puntos de conexión remotos

https://mcp.llmaudit.app/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (2)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢get_visibility_check(runId)

Collect the result of a measurement started with start_visibility_check. Returns status running while the providers are still answering, so poll every 20 to 30 seconds. When ready it reports a verdict, how many of the buyer questions the brand won, which competitors were named instead, and which providers actually answered.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "runId": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "type": "string",
      "description": "From start_visibility_check"
    }
  },
  "required": [
    "runId"
  ]
}
🟢start_visibility_check(brand, website, category, competitors, location, ...)

Measure whether a brand shows up when buyers ask AI assistants for a recommendation. Asks real buyer questions to OpenAI, Anthropic and Gemini and reports what they answered, not what they claim they would answer. Free, no signup, one measurement per domain every 30 days. Returns a runId: call get_visibility_check with it after about a minute. If the domain was already measured this month the response says quota_reached and includes when it ran.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "brand": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "type": "string",
      "minLength": 2,
      "maxLength": 80,
      "description": "Brand name as customers write it"
    },
    "website": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "type": "string",
      "maxLength": 160,
      "description": "Domain, like yourbrand.com"
    },
    "category": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "type": "string",
      "minLength": 2,
      "maxLength": 120,
      "description": "What the business sells, in plain words"
    },
    "competitors": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "description": "Up to 5 real competitors, comma separated",
      "type": "string",
      "maxLength": 220
    },
    "location": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "description": "Where the business competes, like 'Cordoba, Argentina'",
      "type": "string",
      "maxLength": 80
    },
    "language": {
      "$schema": "https://json-schema.org/draft/2020-12/schema",
      "description": "Language the buyer questions are asked in",
      "type": "string",
      "enum": [
        "en",
        "es"
      ]
    }
  },
  "required": [
    "brand",
    "website",
    "category"
  ]
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada2 herramientas
verificadoversión no registrada2 herramientas