# Mikado: Agent-Direct Score C (55.8%)

Site: https://www.sushi.ch/
Report: https://directindex.org/r/mikado.ch
Scanned: 2026-10-14 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Mikado is partly visible to agents.

## Direct links
- Menu: https://mikado.ch/notre-carte/
- Phone: +41223204477

## What to fix first
- **Ordering only through ubereats.** (+12 points) 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
- **Structured data is incomplete.** (+7 points) Missing: address, telephone, opening hours. Guide: https://directindex.org/guides/structured-data-restaurant
- **The server turns AI crawlers away at the door.** (+6.7 points) Live fetches as GPTBot (challenge:access denied), ClaudeBot (challenge:access denied) were refused while a normal browser got the page. This is usually a hosting or firewall bot list the owner never chose. Ask the host to allow these user agents. Guide: https://directindex.org/guides/blocking-ai-crawlers-without-knowing
- **No llms.txt.** (no points, still worth doing) Optional today, cheap to add: a short text file describing the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## 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": "Restaurant",
  "name": "Mikado",
  "url": "https://www.sushi.ch/",
  "telephone": "+41223204477",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Rue de Carouge 8",
    "postalCode": "1205"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 46.1973115,
    "longitude": 6.1429328
  },
  "openingHours": "Mo-Sa 10:00-21:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday"
      ],
      "opens": "10:00",
      "closes": "21:00"
    }
  ],
  "hasMenu": "https://mikado.ch/notre-carte/"
}
</script>
```

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

```
# Mikado

> restaurant in Rue de Carouge 8 1205, Geneva. Phone +41223204477.

## Book or order directly

- Menu: https://mikado.ch/notre-carte/

## Opening hours

Mo-Sa 10:00-21:00

## About

- Website: https://www.sushi.ch/
- This file follows llms.txt (https://llmstxt.org): a short plain-text description for language models.
```

## Already right
- **robots.txt lets AI crawlers in.** No rule blocks the key AI user agents.
- **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.
- **Uber Eats works with agents through its partners.** Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Read 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en. An assistant that is not a partner may not finish the step there; a direct path on your own domain works for all of them.

## Where it stands
115 of 256 in Geneva. Top 45% 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% | no |
| Publish the menu or price list as HTML | 92% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 81% | no |
| Structured data with address, phone and hours | 42% | no |
| Have an llms.txt | 23% | no |

Nearest places in the index: Holy Cow (B, 64 m, https://directindex.org/r/holycow.ch); Bao Canteen (F, 122 m, https://directindex.org/r/baocanteen.com); Sanuki (C, 178 m, https://directindex.org/r/joinoko.com); KHEOPS - Smashburgers (C, 195 m, https://directindex.org/r/kheopsburgers.ch); Petit Prince (B, 203 m, https://directindex.org/r/aupetitprince.ch); La Levantine (C, 239 m, https://directindex.org/r/lalevantine.ch); Caps BBQ (D, 241 m, https://directindex.org/r/capsbbq.ch); Mangia Bene (D, 270 m, https://directindex.org/r/mangiabene-restaurant.ch); UNIMAIL Kitchen (F, 335 m, https://directindex.org/r/sv-gastronomie.ch); Belga (C, 355 m, https://directindex.org/r/fritesbelga.com).

## 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.

Against its peers: Sites built with WordPress 58% (29% A or B, 36926 sites); Sites using Uber Eats 63% (34% A or B, 661 sites); This site 55.8%.

See what an AI agent reads on this site: https://directindex.org/r/mikado.ch/agent-view

Read by AI agents 4 times this month (ClaudeBot 4).

## Businesses like Mikado in Geneva

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in Geneva | 256 | 49% | 26% | 55.8% |
| Built with WordPress in Geneva | 92 | 63% | 36% | 55.8% |
| Using Uber Eats in Geneva | 7 | 55% | 14% | 55.8% |
| Built with WordPress and using Uber Eats in Geneva | 4 | 56% | 25% | 55.8% |

The best of Built with WordPress and using Uber Eats in Geneva: Holy Cow (B 70.8%, https://directindex.org/r/holycow.ch); Tartares & Co (C 66.2%, https://directindex.org/r/tartaresandco.ch); Indian Curry House (F 32.8%, https://directindex.org/r/indian-curryhouse.com).

With the three fixes above (Ordering only through ubereats; Structured data is incomplete; The server turns AI crawlers away at the door) the score would be about 95.4%: 3rd of 256 in Geneva, up from 115th.

## The direct record
What agents get for Mikado, as JSON: https://directindex.org/api/direct/mikado.ch
- Book: none on record
- Order: none on record
- Menu: https://mikado.ch/notre-carte/ (html_page; from the scan)
- Hours: Mo-Sa 10:00-21:00 (open now) (from OpenStreetMap)
- Phone: +41223204477
- Stable links that count: https://directindex.org/go/mikado.ch/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): 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, Uber Eats: Through partners. Uber's US terms of use (12 October 2026) bar scripts that burden the services and any use to build software or train AI; its Claude and ChatGPT integrations only browse menus, with checkout in the Uber Eats app. Read 2026-10-15: https://www.uber.com/legal/en/document/?name=general-terms-of-use&country=united-states&lang=en

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

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 18.3 | 25 |
| Readable | 15 | 25 |
| Actionable | 3 | 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/mikado.ch
- 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: no (how: https://isitagentready.com/.well-known/agent-skills/ai-rules/SKILL.md)
- 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: no (how: https://isitagentready.com/.well-known/agent-skills/llms-txt/SKILL.md)
- 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: yes
- OAuth protected resource metadata: yes
- 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/mikado.ch/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=mikado.ch&force=1
