Maple Voice AI

Audit a restaurant's website and AI visibility, compare call benchmarks, check Maple POS fit.

¿Debería usar esto?

Calidad y seguridad

B
Calidad de la descripción
94%
Integridad del esquema
49%
Calidad de los nombres
98%
Riesgo de envenenamiento
100%
Coincidencia de permisos
100%
Cumplimiento del protocolo
100%

Hallazgos (1)

  • LOWTool 'get_product' description lacks action verben get_product

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

Costo de contexto

~1,822Tokens (definiciones de herramientas)
~518 BTamaño de respuesta típico
Impacto moderado en la atención (1.42% 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": {
    "website": {
      "url": "https://maple.inc/mcp"
    }
  }
}

Puntos de conexión remotos

https://maple.inc/mcpstreamable-http

Qué puede hacer

Inventario de herramientas

Herramientas (11)

🟢 Solo lectura🟡 Escritura🔴 Eliminación⚪ Desconocido
🟢audit_restaurant_site(url)

Use when a restaurant owner or operator asks how their own website looks to customers, search and AI assistants: whether it has a readable menu with prices, consistent phone numbers, hours, Restaurant structured data, online ordering and reservation links, llms.txt, or blocks AI crawlers. Pass the restaurant's website address. Fetches that page, at most two more pages on the same site (a menu page, and an order or reservations page), robots.txt and llms.txt, and returns the facts it found plus `score`: the same score out of 100 the maple.inc/restaurant-website-audit page shows, with its group sub-scores and the checks that need work, most important first. Here the Google listing and page-speed groups are left out (this tool reads only the website) and the other groups scale to 100. It obeys robots.txt, does not run JavaScript, opens no third-party pages, and cannot see Google Business Profile, Yelp or other listings, so a fact missing from the result is "not found in the fetched HTML", not absent. Read-only; does not audit maple.inc.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "url": {
      "type": "string",
      "minLength": 1,
      "maxLength": 2000,
      "description": "The restaurant's own website, for example \"https://joespizza.com\" or \"joespizza.com\". Not a Google, Yelp or delivery-app page."
    }
  },
  "required": [
    "url"
  ]
}
🟢get_call_benchmarks

Use when a restaurant owner asks what is normal for restaurant phone calls: how many calls a day, when calls come in (busiest hours, dayparts and weekdays), how many arrive after hours, what share are orders, and the typical phone order value. Returns Maple's published benchmarks with the window and spread (middle half) of each figure. It does not state how many restaurants, calls or orders sit behind them. The data covers calls Maple answered for its own restaurant customers, not all restaurants, and has no missed-call rate. Read-only.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢check_restaurant_systems(systems)

Use when a restaurant owner or operator asks whether Maple (AI phone answering and phone ordering for restaurants) works with the point-of-sale, online-ordering or reservation systems they use. Pass the system names as plain text. Each one is matched, ignoring case and using common aliases, against the public integrations list on maple.inc. The result says whether Maple lists an integration, with its maple.inc page; names that are not on the list are reported as not listed, never guessed. Read-only: it uses only that public list and needs no account. It does not check live account status or availability for a specific restaurant.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "systems": {
      "minItems": 1,
      "maxItems": 20,
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 80
      },
      "description": "Names of the systems the restaurant uses, as the user wrote them, for example [\"Toast\", \"OpenTable\", \"Foobar POS\"]."
    }
  },
  "required": [
    "systems"
  ]
}
🟢estimate_missed_call_revenue(callsPerDay, missedCallPercent, averageOrderValue, operatingDaysPerMonth, orderCallPercent, ...)

Use only when the user supplies their own call volume and asks what missed phone calls may cost a restaurant. Runs the same model as the maple.inc ROI calculator on the numbers given: calls per day, the share missed and average order value, plus optional assumptions that otherwise use the calculator's illustrative defaults. Returns an illustrative estimate of order sales from missed calls with every assumption shown. It is a scenario, not a measured result or a guarantee, and it leaves out reservations and catering. Read-only arithmetic.

Esquema de entrada

{
  "type": "object",
  "properties": {
    "callsPerDay": {
      "type": "number",
      "minimum": 0,
      "maximum": 5000,
      "description": "Inbound phone calls per day."
    },
    "missedCallPercent": {
      "type": "number",
      "minimum": 0,
      "maximum": 100,
      "description": "Share of calls that go unanswered, 0-100."
    },
    "averageOrderValue": {
      "type": "number",
      "minimum": 0,
      "maximum": 10000,
      "description": "Average phone order value in dollars."
    },
    "operatingDaysPerMonth": {
      "description": "Days open per month. Default 30.",
      "type": "number",
      "minimum": 1,
      "maximum": 31
    },
    "orderCallPercent": {
      "description": "Share of missed calls that were order requests. Default 50.",
      "type": "number",
      "minimum": 0,
      "maximum": 100
    },
    "capturedOrderPercent": {
      "description": "Share of those order requests that would become completed orders. Default 50.",
      "type": "number",
      "minimum": 0,
      "maximum": 100
    }
  },
  "required": [
    "callsPerDay",
    "missedCallPercent",
    "averageOrderValue"
  ]
}
🟢get_product_status

Use when someone asks what Maple offers and which products are available now versus early access or beta: the phone agent, Ordering Sites, Maple GM, Fleet delivery, drive-thru and kiosk. Returns each product's current status exactly as published on maple.inc. Read-only.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_pricing

Published Maple Voice, Maple Pro, and Maple Enterprise prices. No per-minute fees.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_demo_booking_link

Use when a restaurant owner or operator wants to talk to Maple, see a demo, get set up or get a quote. Returns the maple.inc booking page and what the person will be asked for. Read-only: it does not book, submit a form or contact Maple, so give the link to the person and let them book the time themselves. Existing Maple customers who need help should use the Help Center link in the result instead.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢list_integrations

The full list of POS and reservation systems Maple writes phone orders and bookings into.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_product

What Maple Voice AI is and who it is for (restaurants, POS, reservations).

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_site_index

Maple.inc page index for agents: llms.txt, sitemap, docs, OpenAPI, and the MCP card.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}
🟢get_developer_resources

Maple developer resources: OpenAPI, API catalog, docs, help, webhooks pointer, and this MCP server.

Esquema de entrada

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

Comunidad

Califica este servidor

Evidencia

Observaciones recientes

verificadoversión no registrada11 herramientas