# Krušovická restaurace Na Michelské: Agent-Direct Score B (70.8%)

Site: https://michelska.cz/
Report: https://directindex.org/r/michelska.cz
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.)
Krušovická restaurace Na Michelské is mostly ready for agents.
An AI assistant can open the website of Krušovická restaurace Na Michelské. It can read what Krušovická restaurace Na Michelské offers. To book or order, it is sent to Wolt, a marketplace.

## Direct links
- Menu: https://michelska.cz/menu/
- Phone: +420 241 480 611

## What to fix first
- **Ordering only through wolt.** (+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
- **Wolt's terms bar bots and automated use; a direct form on your own site has no such limit.** (+12 points) Wolt's user terms (Germany, from 8 September 2025) say users must not use bots or other automated methods to use the Wolt services and must access them only through Wolt's own app and website. Read 2026-10-15: https://explore.wolt.com/en/deu/terms. An agent that books or orders there acts outside the vendor's terms unless the vendor permits it; a form or booking page on your own domain has no such limit. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **Structured data is incomplete.** (+4 points) Missing: address, telephone. Guide: https://directindex.org/guides/structured-data-restaurant
- **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": "Krušovická restaurace Na Michelské",
  "url": "https://michelska.cz/",
  "telephone": "+420 241 480 611",
  "email": "michelska@post.cz",
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 50.0470774,
    "longitude": 14.4607453
  },
  "openingHours": "Mo-Su 11:00-22:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [],
      "opens": "11:00",
      "closes": "22:00"
    }
  ],
  "hasMenu": "https://michelska.cz/menu/"
}
</script>
```

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

```
# Krušovická restaurace Na Michelské

> restaurant in Prague. Phone +420 241 480 611.

## Book or order directly

- Menu: https://michelska.cz/menu/

## Opening hours

Mo-Su 11:00-22:00

## About

- Website: https://michelska.cz/
- 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.
- **AI crawlers get the page.** GPTBot, ClaudeBot and PerplexityBot all received a normal response.
- **Structured data present (Restaurant).** opening hours
- **Menu or price list is an HTML page.** Agents can read items and prices directly.

## Where it stands
117 of 1125 in Prague. Top 10% 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 | 50% | no |
| Publish the menu or price list as HTML | 82% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 99% | yes |
| Structured data with address, phone and hours | 48% | no |
| Have an llms.txt | 34% | no |

Nearest places in the index: Dian (C, 345 m, https://directindex.org/r/dianrestaurant.cz); Dock House (B, 372 m, https://directindex.org/r/dockhouse.cz); Červená cibule (D, 384 m, https://directindex.org/r/cervena-cibule.cz); Restaurace U Ztracenejch (F, 394 m, https://directindex.org/r/uztracenejch.cz); Maranatha (D, 413 m, https://directindex.org/r/restauracemaranatha.cz); U Kubíka (F, 413 m, https://directindex.org/r/ukubika.cz); ne-SMYSL (D, 459 m, https://directindex.org/r/restaurantnesmysl.cz); Sparta (C, 554 m, https://directindex.org/r/restaurace-sparta.cz); Na Kopečku (D, 645 m, https://directindex.org/r/restaurace-nakopecku.cz); Bulldog’s dart pub (F, 671 m, https://directindex.org/r/bulldogspub.cz).

## 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 Wolt 59% (22% A or B, 381 sites); This site 70.8%.

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

## Businesses like Krušovická restaurace Na Michelské in Prague

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Prague | 1125 | 45% | 11% | 70.8% |
| Sites built with WordPress in Prague | 345 | 53% | 12% | 70.8% |
| Sites using Wolt in Prague | 29 | 55% | 17% | 70.8% |
| Sites built with WordPress and using Wolt in Prague | 17 | 58% | 24% | 70.8% |

The best of the sites built with WordPress and using Wolt in Prague: Gutovka (B 76.9%, https://directindex.org/r/restauracegutovka.cz); Samarkand Kebab (B 76.9%, https://directindex.org/r/samarkandkebab.cz); Lehká hlava (B 75%, https://directindex.org/r/lehkahlava.cz); Podolská kotva (C 66.2%, https://directindex.org/r/podolskakotva.cz); Pizzeria La Ventola (C 58.9%, https://directindex.org/r/laventola.cz).

With the three fixes above (Ordering only through wolt; Wolt's terms bar bots and automated use; a direct form on your own site has no such limit; Structured data is incomplete) the score would be about 100%: first of 1,125 in Prague.

## The direct record
What agents get for Krušovická restaurace Na Michelské, as JSON: https://directindex.org/api/direct/michelska.cz
- Book: none on record
- Order: none on record
- Menu: https://michelska.cz/menu/ (html_page; from the scan)
- Hours: Mo-Su 11:00-22:00 (open now) (from OpenStreetMap)
- Phone: +420 241 480 611
- Stable links that count: https://directindex.org/go/michelska.cz/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, Wolt: No. Wolt's user terms (Germany, from 8 September 2025) say users must not use bots or other automated methods to use the Wolt services and must access them only through Wolt's own app and website. Read 2026-10-15: https://explore.wolt.com/en/deu/terms

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

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 25 | 25 |
| Readable | 18 | 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/michelska.cz
- 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: 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: 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

Keep watching this business (https://directindex.org/r/michelska.cz/plan): the assistants asked again every month, with what changed; 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/michelska.cz/deep. Ten questions the way people ask, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF: 5 EUR, one-off. Reading and scanning stay free; these few euros pay for the questions sent to the assistants and for the servers.
Methodology: https://directindex.org/methodology · Rescan now: https://directindex.org/scan?url=michelska.cz&force=1
