The Direct Index
Report · New York · scanned 2026-10-14

Kababish

kababish.com is hard for agents to use.

Menu: www.kababish.com/menu.php

See what an AI agent reads on this site →

D
52.3%

34 of 65 points available

0/5

agent-readiness level, Not Ready

4

things to fix

Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.

Findings

What to fix first

  1. No structured data for the business +14 points

    Add schema.org JSON-LD for the business (Restaurant, LocalBusiness or the closest type, with name, address, telephone and openingHoursSpecification, plus servesCuisine and acceptsReservations). It is the one block every assistant reads first; the fix kit below has it filled in. How to fix it

  2. Ordering only through grubhub +12 points

    Every agent transaction goes through the marketplace and its commission. Add a direct path on your own site, even a simple form. How to fix it About this vendor

  3. Almost no text without JavaScript +2 points

    Crawlers that do not run scripts see an empty page. Render the menu, hours and address as plain HTML. How to fix it

  4. No llms.txt no points, still worth doing

    Optional today, cheap to add: a short text file describing the business for language models. How to fix it

No one is listed yet to fix this in New York. List your agency or yourself: free, reviewed by hand.

Already right

Builder: unknown · Front: cloudflare

Fix kit

What to paste

Filled from the business's own record and this scan. Check every line before it goes live; where it goes on your builder is in the guides.

Structured data (JSON-LD)

One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong. Guide.

<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Restaurant",
  "name": "Kababish",
  "url": "https://www.kababish.com/",
  "telephone": "+1 718-565-5131",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Broadway 70-64",
    "postalCode": "11372",
    "addressLocality": "Jackson Heights"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 40.7476177,
    "longitude": -73.893979
  },
  "openingHours": "Mo-Su 09:00-05:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [],
      "opens": "09:00",
      "closes": "05:00"
    }
  ],
  "servesCuisine": [
    "indian",
    "bengali",
    "pakistani"
  ],
  "hasMenu": "https://www.kababish.com/menu.php"
}
</script>

llms.txt

Save as /llms.txt at the root of the site. Guide.

# Kababish

> restaurant (indian, bengali, pakistani) in Broadway 70-64 11372 Jackson Heights, New York. Phone +1 718-565-5131.

## Book or order directly

- Menu: https://www.kababish.com/menu.php

## Opening hours

Mo-Su 09:00-05:00

## About

- Website: https://www.kababish.com/
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
Where it stands

2,511 of 4,817 in New York

Top 52% of the sites scanned in this index. Just above: Ital Kitchen D, Jumbo Bagels D. Just below: La Puerta Roja D, On The Border D.

What the top tenth of the index doesTop 10%This site
Take bookings or orders on their own domain100%no
Publish the menu or price list as HTML97%yes
Let AI crawlers in (no edge block, no robots.txt block)94%yes
Structured data with address, phone and hours49%no
Have an llms.txt13%no

The top tenth is the 488 best-scoring reachable sites of the index at the last refresh.

Against its peers

Average scoreA or BThis site
Sites using Grubhub 140 sites66%46%52.3%

Nearest places with a similar menu

PlaceDistanceGradeDirect booking or ordering
Dera indian, nepali, pakistani, bengali43 mAyes
Kabab King bangladeshi, indian, pakistani149 mDno
Cardamom indian2.3 kmCyes
Tikka Indian Grill indian2.9 kmByes
Aroma Indian indian3.4 kmDno
Bombay Grill House 3 indian4.4 kmByes
Businesses like yours

Businesses like Kababish in New York

GroupSitesAvg scoreA or BThis site
Same kind in New York4,81746%36%52.3%
Using Grubhub in New York7366%42%52.3%

The best of Using Grubhub in New York

Club A Steakhouse A 100% · Bartolino's Italian Restaurant A 95.4% · Myrtle Thai A 95.4% · Savelli A 95.4% · La Locanda A 93.8%

The climb

With the three fixes above (No structured data for the business; Ordering only through grubhub; Almost no text without JavaScript) the score would be about 95.4%: 74th of 4,817 in New York, up from 2511th.

Peers are the businesses of the same index with a reachable site, latest scan of each; the rank uses the index's current ranking.

The direct record

What agents get for Kababish

The links an assistant is sent when it books, orders or reads the menu for this business, where each leads, and when a browser last checked it. The same record is served as JSON at /api/direct/kababish.com, through the MCP tool direct_record and in the city feed /city/new-york/direct.json.

PathLinkStatus
Booknone on record
Ordernone on record
Menuwww.kababish.com/menu.php html_pagefrom the scan
HoursMo-Su 09:00-05:00 (open now)from OpenStreetMap
Phone+1 718-565-5131

Stable links that count: /go/kababish.com/menu answer 302 to the links above; the count is the line "followed N direct links" on this page.

Owners: claim the business below to correct this record; the claim email carries the link.

Transactable

Can an agent transact?

Measured, not scored: the Agent-Direct Score stays at specification v1.0. This says which rails an agent could transact through today, and what the booking or ordering vendor's terms allow.

UCP profile
/.well-known/ucp, Google and Shopify's Universal Commerce Protocol
not measured
ACP discovery document
/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol
not measured
MCP server card
/.well-known/mcp/server-card.json
no
Ordering vendor that takes agent orders
Square, Toast, or a vendor whose terms allow agents
not measured
Vendor terms for agents
Grubhub, read 2026-10-15
Partners only

Not measured at this scan; the next scan measures it.

Grubhub's terms of use (17 December 2024) bar access with any robot, spider, crawler or automated process; since June 2026 Alexa+ users can browse, build an order and check out through Grubhub by voice. Source. About Grubhub · all vendors.

The next scan also reads the contact, menu and booking pages one hop deeper; facts found there can change the score.

Agent readiness

Level 0 of 5, Not Ready

The standards an agent looks for before it reads a page, on the same criteria as Cloudflare's Agent Readiness scan. Not part of the score; each missing item links to a how-to. Cloudflare's report.

Link headers on the homepageno how
sitemap.xmlno how
AI bot rules in robots.txtno how
Content Signals in robots.txtno how
Markdown on Accept: text/markdownno how
llms.txtno how
API catalog (RFC 9727)no how
MCP server cardno how
A2A agent cardno how
Agent Skills indexno how
OAuth or OIDC discoveryno how
OAuth protected resource metadatano how
auth.mdno how
Web Bot Auth key directoryno how
ARD capability manifestno how
DNS-AID recordsno how
WebMCP tools on the pageno how
JSON-LD for the businessno
Assistants

What assistants answer

Each assistant is asked three questions about this business: the official website, where to book, where to order. The cell says where the answer sent people.

Not asked yet. Assistants are asked about the top-ranked businesses in each city index, and about every claimed business the moment it is claimed; claim this page to be included.

Badge

Show the score

Owners who score well embed the badge; it links back here and updates with every scan.

Agent-Direct Score D

<a href="https://directindex.org/r/kababish.com"><img src="https://directindex.org/badge/kababish.com.svg" alt="Agent-Direct Score D" width="236" height="40"></a>
Owners

Own this business?

Fixed something, or think a check is wrong? Rescans are free. Claiming takes one email to confirm; after that the three assistants are asked about the business right away, the site is rescanned weekly, and you get a message only when the score changes.

Rescan now Markdown

Deep report Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 19 EUR, one-off.

Send the fixes to your web person
One email, the fixes and the link; nothing stored.