MCP MeasureMCP Measure

índice observado

Trust Live

Evidence-linked MCP selection and non-executing Safe-Call review; surfaces unknowns.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
82%
Integridad del esquema
87%
Calidad de los nombres
92%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Hallazgos (1)

  • LOWTool 'compare_providers' description lacks action verben compare_providers

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

Costo de contexto

~735Tokens (definiciones de herramientas)
~1.2 KBTamaño de respuesta típico
Impacto moderado en la atención (0.57% 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": {
    "trust-live": {
      "url": "https://mcp-selection-lab-production.up.railway.app/trust-live/mcp"
    }
  }
}

Puntos de conexión remotos

https://mcp-selection-lab-production.up.railway.app/trust-live/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (5)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢recommend_provider(task_requirements)

Recommend a provider with hard-filter outcomes, component scores, evidence, and Safe-Call constraints.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "task_requirements": {
      "additionalProperties": true,
      "description": "Structured capability, operation, auth, payment, data and evidence requirements.",
      "title": "Task Requirements",
      "type": "object"
    }
  },
  "required": [
    "task_requirements"
  ],
  "title": "recommend_providerArguments"
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true,
  "title": "recommend_providerDictOutput"
}
🟢compare_providers(task_requirements)

Compare matching providers across capability, verification, safety, payment, freshness and unknowns.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "task_requirements": {
      "additionalProperties": true,
      "description": "Structured task requirements.",
      "title": "Task Requirements",
      "type": "object"
    }
  },
  "required": [
    "task_requirements"
  ],
  "title": "compare_providersArguments"
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true,
  "title": "compare_providersDictOutput"
}
🟢get_provider_profile(provider_id)

Get a canonical provider profile with capabilities, evidence references, and safe-call contracts.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "provider_id": {
      "maxLength": 128,
      "minLength": 1,
      "title": "Provider Id",
      "type": "string"
    }
  },
  "required": [
    "provider_id"
  ],
  "title": "get_provider_profileArguments"
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true,
  "title": "get_provider_profileDictOutput"
}
🟢get_capability(capability_id)

Get every provider capability with this canonical action ID, including evidence and Safe-Call contract.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "capability_id": {
      "maxLength": 128,
      "minLength": 1,
      "title": "Capability Id",
      "type": "string"
    }
  },
  "required": [
    "capability_id"
  ],
  "title": "get_capabilityArguments"
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true,
  "title": "get_capabilityDictOutput"
}
🟢evaluate_safe_call(provider_id, capability_id, arguments, user_confirmed, repository_visibility, ...)

Evaluate Safe-Call constraints without invoking the provider tool.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "provider_id": {
      "maxLength": 128,
      "minLength": 1,
      "title": "Provider Id",
      "type": "string"
    },
    "capability_id": {
      "maxLength": 128,
      "minLength": 1,
      "title": "Capability Id",
      "type": "string"
    },
    "arguments": {
      "additionalProperties": true,
      "description": "Proposed arguments; evaluated locally and never sent to the provider.",
      "title": "Arguments",
      "type": "object"
    },
    "user_confirmed": {
      "default": false,
      "title": "User Confirmed",
      "type": "boolean"
    },
    "repository_visibility": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Repository Visibility"
    },
    "data_classes": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "title": "Data Classes"
    }
  },
  "required": [
    "provider_id",
    "capability_id",
    "arguments"
  ],
  "title": "evaluate_safe_callArguments"
}

Esquema de salida

{
  "type": "object",
  "additionalProperties": true,
  "title": "evaluate_safe_callDictOutput"
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada5 herramientas