# KUMI: Agent-Direct Score B (84.6%)

Site: https://www.kumi.no
Report: https://directindex.org/r/kumi.no
Scanned: 2026-10-15 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
KUMI is mostly ready for agents.

## Direct links
- Book directly: https://kumi.no/events/ (on the business's own site)
- Menu: https://kumi.no/brunch
- Phone: +4797302866

## What to fix first
- **Structured data is incomplete.** (+7 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **Ordering only through wolt.** (no points, still worth doing) Every agent transaction goes through the marketplace and its commission. Add a direct path on your own site, even a simple form. Guide: https://directindex.org/guides/online-ordering-without-delivery-apps

## Fix kit: What to paste

Structured data (JSON-LD). One block in the page's head, or in the builder's custom-code slot. Replace anything that is wrong.

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "CafeOrCoffeeShop",
  "name": "KUMI",
  "url": "https://www.kumi.no",
  "telephone": "+4797302866",
  "email": "kumi@kumi.no",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 59.908429,
    "longitude": 10.769455
  },
  "openingHours": "Mo-Fr 10:00-17:00; Sa-Su 10:00-17:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday"
      ],
      "opens": "10:00",
      "closes": "17:00"
    },
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Saturday",
        "Sunday"
      ],
      "opens": "10:00",
      "closes": "17:00"
    }
  ],
  "servesCuisine": [
    "plantbased",
    "brunch",
    "organic"
  ],
  "acceptsReservations": "https://kumi.no/events/",
  "hasMenu": "https://kumi.no/brunch",
  "potentialAction": [
    {
      "@type": "ReserveAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://kumi.no/events/",
        "actionPlatform": [
          "http://schema.org/DesktopWebPlatform",
          "http://schema.org/MobileWebPlatform"
        ]
      },
      "result": {
        "@type": "Reservation",
        "name": "Reservation"
      }
    }
  ]
}
</script>
```

## Already right
- **robots.txt lets AI crawlers in.** No rule blocks the key AI user agents.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Structured data present (Organization).** but without address, phone or hours
- **Menu or price list is an HTML page.** Agents can read items and prices directly.
- **Booking on your own site.** Agents can book without a marketplace in the loop.

## Since the scan of 2026-10-14 (C then)
- Fixed: The server turned AI crawlers away at the door; No booking or ordering path at all
- New: Ordering only through a marketplace

## Where it stands
2 of 216 in Oslo cafes and bars. Top 1% of the sites scanned in this index.

| What the top tenth of the index does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 100% | yes |
| Publish the menu or price list as HTML | 41% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 100% | yes |
| Structured data with address, phone and hours | 9% | no |
| Have an llms.txt | 18% | yes |

Nearest places in the index: Bernie's (D, 86 m, https://directindex.org/r/bernies.no); Preik (F, 228 m, https://directindex.org/r/preikoslo.no); Brostein (C, 277 m, https://directindex.org/r/brosteinbar.no); Fuglen Gamlebyen (F, 381 m, https://directindex.org/r/fuglen.no); Grønland Boulebar & Spiseri (B, 397 m, https://directindex.org/r/gronlandboule.no); Spillbaren (F, 482 m, https://directindex.org/r/spillbaren.no); Oslo Mekaniske Verksted (C, 514 m, https://directindex.org/r/oslomekaniskeverksted.no); Galgen (D, 573 m, https://directindex.org/r/galgen.no); Lille Betong (D, 595 m, https://directindex.org/r/restaurantbetong.no); Papegøye (D, 605 m, https://directindex.org/r/prettybird.no).

## What assistants answer
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.

Score over 2 scans since 2026-10-14: 2026-10-14 57%, 2026-10-15 85%.

Against its peers: Sites built with WordPress 58% (29% A or B, 36926 sites); Sites using Wolt 59% (22% A or B, 381 sites); This site 84.6%.

See what an AI agent reads on this site: https://directindex.org/r/kumi.no/agent-view

## Businesses like KUMI in Oslo cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in Oslo cafes and bars | 216 | 48% | 14% | 84.6% |
| Built with WordPress in Oslo cafes and bars | 45 | 55% | 20% | 84.6% |
| Using Wolt in Oslo cafes and bars | 2 | 64% | 50% | 84.6% |
| Built with WordPress and using Wolt in Oslo cafes and bars | 1 | 85% | 100% | 84.6% |

The best of Built with WordPress in Oslo cafes and bars: Bakerina (B 75.4%, https://directindex.org/r/bakerina.no); Fjær Konfekt (B 73.8%, https://directindex.org/r/fjaerkonfekt.no); Pokalen Parkveien (B 72.5%, https://directindex.org/r/pokalenpub.no); Bohemen (B 70%, https://directindex.org/r/bohemen.no); Den Gamle Major (B 70%, https://directindex.org/r/gamlemajor.no).

With the fix above (Structured data is incomplete) the score would be about 95.4%: first of 216 in Oslo cafes and bars.

## The direct record
What agents get for KUMI, as JSON: https://directindex.org/api/direct/kumi.no
- Book: https://kumi.no/events/ (own site; found by the scan of 2026-10-15, not yet tested)
- Order: none on record
- Menu: https://kumi.no/brunch (html_page; from the scan)
- Hours: Mo-Fr 10:00-17:00; Sa-Su 10:00-17:00 (open now) (from OpenStreetMap)
- Phone: +4797302866
- Stable links that count: https://directindex.org/go/kumi.no/book, https://directindex.org/go/kumi.no/menu

## Can an agent transact?
Measured, not scored (the score stays at spec v1.0).
- UCP profile (/.well-known/ucp, Google and Shopify's Universal Commerce Protocol): no
- ACP discovery document (/.well-known/acp.json, OpenAI and Stripe's Agentic Commerce Protocol): no
- 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): no

Found one hop past the home page: menu page /brunch: ordering via wolt.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 15 | 25 |
| Actionable | 15 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 1 of 5, Basic Web Presence. Cloudflare's report: https://isitagentready.com/kumi.no
- Link headers on the homepage: no (how: https://isitagentready.com/.well-known/agent-skills/link-headers/SKILL.md)
- sitemap.xml: yes
- AI bot rules in robots.txt: yes
- Content Signals in robots.txt: no (how: https://isitagentready.com/.well-known/agent-skills/content-signals/SKILL.md)
- Markdown on Accept: text/markdown: no (how: https://isitagentready.com/.well-known/agent-skills/markdown-negotiation/SKILL.md)
- llms.txt: yes
- API catalog (RFC 9727): no (how: https://isitagentready.com/.well-known/agent-skills/api-catalog/SKILL.md)
- MCP server card: no (how: https://isitagentready.com/.well-known/agent-skills/mcp-server-card/SKILL.md)
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: no (how: https://isitagentready.com/.well-known/agent-skills/agent-skills/SKILL.md)
- OAuth or OIDC discovery: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-discovery/SKILL.md)
- OAuth protected resource metadata: no (how: https://isitagentready.com/.well-known/agent-skills/oauth-protected-resource/SKILL.md)
- auth.md: no (how: https://isitagentready.com/.well-known/agent-skills/auth-md/SKILL.md)
- Web Bot Auth key directory: no (how: https://isitagentready.com/.well-known/agent-skills/web-bot-auth/SKILL.md)
- ARD capability manifest: no (how: https://isitagentready.com/.well-known/agent-skills/ard/SKILL.md)
- DNS-AID records: no (how: https://isitagentready.com/.well-known/agent-skills/dns-aid/SKILL.md)
- WebMCP tools on the page: no (how: https://isitagentready.com/.well-known/agent-skills/webmcp/SKILL.md)
- JSON-LD for the business: yes

Deep report: https://directindex.org/r/kumi.no/deep. 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.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=kumi.no&force=1