OmniProvider

Pay-per-call LLM API for agents: model catalog, pricing, unpaid x402/MPP quotes, how-to-pay.

¿Debería usar esto?

Calidad y seguridad

A
Calidad de la descripción
100%
Integridad del esquema
89%
Calidad de los nombres
80%
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

~645Tokens (definiciones de herramientas)
~811 BTamaño de respuesta típico
Impacto moderado en la atención (0.50% 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": {
    "omniprovider": {
      "url": "https://mcp.omnidev.tech/mcp"
    }
  }
}

Puntos de conexión remotos

https://mcp.omnidev.tech/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (4)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢omniprovider_list_models(tier)

Returns the public catalog: model ids, context windows, maximum output tokens, price per million input and output tokens, accepted payment rails and prepaid packs that can be bought now.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "tier": {
      "type": "string",
      "enum": [
        "open",
        "frontier"
      ],
      "description": "Optional filter by catalog tier."
    }
  },
  "additionalProperties": false
}
🟢omniprovider_get_pricing(model, input_tokens, output_tokens)

Returns prices: fixed per-call prices of the nano, small and brief routes, and per-token prices of the catalog. With a model and token counts it also returns an estimated cost and the minimum charge per rail.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "maxLength": 64,
      "description": "Catalog model id."
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "maximum": 2000000
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "maximum": 200000
    }
  },
  "additionalProperties": false
}
🟢omniprovider_get_quote(route, body)

Sends one unpaid request to a paid route and returns the 402 payment requirements (amount, currency, network, payee, protocol). No payment is made and no credential is sent; the response is the quote for that exact request body.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "route": {
      "type": "string",
      "enum": [
        "/v1/chat/nano",
        "/v1/chat/small",
        "/v1/brief",
        "/v1/chat/completions",
        "/x402/chat-nano",
        "/x402/chat-small",
        "/x402/brief"
      ],
      "description": "Paid route path. /v1/* accepts MPP, /x402/* accepts x402."
    },
    "body": {
      "type": "object",
      "description": "JSON request body the quote is computed for (messages or prompt; for /v1/chat/completions also model and max_tokens)."
    }
  },
  "required": [
    "route",
    "body"
  ],
  "additionalProperties": false
}
🟢omniprovider_how_to_pay(rail)

Returns the payment flow for a rail: endpoint URL, required headers, the client nonce format, and client commands. Payment is produced by the caller's own wallet tooling; this server holds no keys.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "rail": {
      "type": "string",
      "enum": [
        "mpp",
        "x402",
        "package",
        "card"
      ],
      "description": "Payment rail; all rails when omitted."
    }
  },
  "additionalProperties": false
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada4 herramientas