# Opson: Agent-Direct Score F (39.5%)

Site: https://www.opson.de/
Report: https://directindex.org/r/opson.de
Scanned: 2026-10-14 (provisional: the action test and the assistant citation check pending)
Opson is largely invisible to agents.

## Direct links
- Menu: https://www.opson.de/wp-content/uploads/2025/04/opson_speisekarte_2025_web.pdf

## What to fix first, by points
- **No structured data for the business.** (+15 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. Guide: https://directindex.org/guides/structured-data-restaurant
- **No booking or ordering path at all.** (+15 points) Agents have nothing to act on. Add a booking or ordering page on your own domain. Guide: https://directindex.org/guides/book-direct-on-your-own-website
- **The server turns AI crawlers away at the door.** (+3.3 points) Live fetches as ClaudeBot (http_403) 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
- **Menu or price list is a PDF.** (+3 points) Most agents skip PDFs or read them badly. Publish it as HTML, keep the PDF as a download. Guide: https://directindex.org/guides/menu-pdf-ai
- **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, one block in the page head:

```html
<script type="application/ld+json">
{
  "@context": "https://schema.org",
  "@type": "Restaurant",
  "name": "Opson",
  "url": "https://www.opson.de/",
  "address": {
    "@type": "PostalAddress",
    "streetAddress": "Trappentreustraße 33",
    "postalCode": "80339",
    "addressLocality": "München",
    "addressCountry": "DE"
  },
  "geo": {
    "@type": "GeoCoordinates",
    "latitude": 48.1350663,
    "longitude": 11.5344127
  },
  "openingHours": "Mo-Sa 17:00-01:00; Su 11:00-01:00",
  "openingHoursSpecification": [
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Monday",
        "Tuesday",
        "Wednesday",
        "Thursday",
        "Friday",
        "Saturday"
      ],
      "opens": "17:00",
      "closes": "01:00"
    },
    {
      "@type": "OpeningHoursSpecification",
      "dayOfWeek": [
        "Sunday"
      ],
      "opens": "11:00",
      "closes": "01:00"
    }
  ],
  "servesCuisine": [
    "greek"
  ],
  "hasMenu": "https://www.opson.de/wp-content/uploads/2025/04/opson_speisekarte_2025_web.pdf"
}
</script>
```

llms.txt draft:

```
# Opson

> restaurant (greek) in Trappentreustraße 33 80339 München, Munich.

## Book or order directly

- Menu: https://www.opson.de/wp-content/uploads/2025/04/opson_speisekarte_2025_web.pdf

## Opening hours

Mo-Sa 17:00-01:00; Su 11:00-01:00

## About

- Website: https://www.opson.de/
- 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.

## Where it stands
Rank 1236 of 1863 in Munich (top 66%).

| What the top tenth does | Top 10% | This site |
|---|---|---|
| Take bookings or orders on their own domain | 94% | no |
| Publish the menu or price list as HTML | 84% | no |
| Let AI crawlers in (no edge block, no robots.txt block) | 85% | no |
| Structured data with address, phone and hours | 37% | no |
| Have an llms.txt | 21% | no |

Nearest places with a similar menu: Restaurant Athen (B, 1354 m, https://directindex.org/r/restaurant-athen.de); Taverne Armonia (F, 1644 m, https://directindex.org/r/taverne-armonia.de); Athene (B, 1891 m, https://directindex.org/r/athene-muenchen.de); In Mamas Küche (C, 2033 m, https://directindex.org/r/inmamaskueche.de); Taverna Melina Merkouri (B, 2162 m, https://directindex.org/r/taverna-melina.de); Tou Bakali (D, 2429 m, https://directindex.org/r/tou-bakali-laim.de); Taverna Cyclades (C, 2487 m, https://directindex.org/r/cyclades-muenchen.de); Medusa (D, 2637 m, https://directindex.org/r/medusamunchen.de); Irodion (D, 2738 m, https://directindex.org/r/sendling-irodion.de); Restaurant Poseidon (F, 2773 m, https://directindex.org/r/poseidon-leonrod.de).

## What assistants answer
Not asked yet. Assistants are asked about the top-ranked and claimed businesses in each city index.

Against its peers: Sites built with WordPress average 57% (26% A or B, 35830 sites); this site 39.5%.

What an AI agent reads on this site: https://directindex.org/r/opson.de/agent-view

## Score breakdown
| Component | Points | Available |
|---|---|---|
| reachable | 21.7 | 25 |
| readable | 4 | 25 |
| actionable | 0 | 15 (action_test pending) |
| cited | 0 | 0 (probes pending) |

## Agent readiness (Cloudflare criteria)
Level 1 of 5: Basic Web Presence. Cloudflare's report: https://isitagentready.com/opson.de
- 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: no

Methodology: https://directindex.org/methodology · Rescan: https://directindex.org/scan?url=opson.de&force=1