Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Maple Voice AI

REMOTE · MAPLE.INC

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

Available components

+3 this week 75 Trust /100

Last scanned (14 hours ago)

Scores higher than 62% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security74
  • The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
  • No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
  • HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
  • HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
  • DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
Schema Quality & AI Usability73
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1271 tokens (~115/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
  • Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 15 Nov 26 +1
    • Tool “get_product_status” rewrote its description, which is the text the model reads security
  • 14 Nov 26 0
    • Server version: 1.3.0 → 1.4.1 functional
    • New tool “get_demo_booking_link” functional
  • 13 Nov 26 +1
    • Tool “get_call_benchmarks” rewrote its description, which is the text the model reads security
    • Tool “audit_restaurant_site” rewrote its description, which is the text the model reads security
    • Server version: 1.2.0 → 1.3.0 functional
  • 12 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: pass → fail ▼ functional
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 1.1.0 → 1.2.0 functional
    • New tool “audit_restaurant_site” functional
    • New tool “get_call_benchmarks” functional
  • 11 Nov 26 70

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Probed https://maple.inc/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=maple.inc CN=WE1,O=Google Trust Services,C=US 20 Nov 2026 18 Feb 2027 ECDSA 256 ECDSA-SHA256 dd3fe5a697aa62af1313d01108bb7066
SANs: maple.inc, kiosk.dunkin.maple.inc, *.kiosk.dunkin.maple.inc
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of maple.inc. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
inc. DS published 13114, 18077 8, 8 Verified
maple.inc. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://maple.inc/mcp Verified 200
http (plaintext) http://maple.inc/mcp HTTPS enforced 301 https://maple.inc/mcp
MCP tools · 11 exposed · ~1,090 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
audit_restaurant_site ~277

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.

NameTypeReqDescription
urlstringyesThe restaurant's own website, for example "https://joespizza.com" or "joespizza.com". Not a Google, Yelp or delivery-app page.

No output schema declared.

No examples provided.

check_restaurant_systems ~170

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.

NameTypeReqDescription
systemsarrayyesNames of the systems the restaurant uses, as the user wrote them, for example ["Toast", "OpenTable", "Foobar POS"].

No output schema declared.

No examples provided.

estimate_missed_call_revenue ~224

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.

NameTypeReqDescription
averageOrderValuenumberyesAverage phone order value in dollars.
callsPerDaynumberyesInbound phone calls per day.
capturedOrderPercentnumber–Share of those order requests that would become completed orders. Default 50.
missedCallPercentnumberyesShare of calls that go unanswered, 0-100.
operatingDaysPerMonthnumber–Days open per month. Default 30.
orderCallPercentnumber–Share of missed calls that were order requests. Default 50.

No output schema declared.

No examples provided.

get_call_benchmarks ~123

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_demo_booking_link ~97

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_developer_resources ~33

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_pricing ~26

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_product ~25

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_product_status ~58

Use when someone asks what Maple offers and the status of each product: 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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

get_site_index ~32

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_integrations ~25

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Maple Voice AI MCP server?

Maple Voice AI is a hosted endpoint at https://maple.inc/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · maple.inc

# add to Claude Code
claude mcp add --transport http inc-maple-website 'https://maple.inc/mcp'
Common questions

What is the Maple Voice AI MCP server?

Maple Voice AI is an MCP server listed in the public MCP registry as inc.maple/website. Audit a restaurant's website and AI visibility, compare call benchmarks, check Maple POS fit. This page covers its hosted endpoint (https://maple.inc/mcp).

Is the Maple Voice AI MCP server safe to use?

Maple Voice AI scores 75 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Maple Voice AI MCP server expose?

Maple Voice AI exposes 11 tools: audit_restaurant_site, get_call_benchmarks, check_restaurant_systems, estimate_missed_call_revenue, get_product_status, and 6 more. Their descriptions and schemas cost roughly 1,090 tokens of context every time the server is loaded.

Does the Maple Voice AI MCP server require authentication?

No. We connected to Maple Voice AI without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Maple Voice AI MCP server still maintained?

Maple Voice AI is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Maple Voice AI MCP server?

VerifyMCP ran 13 checks on Maple Voice AI, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.