# Santorini: Agent-Direct Score B (73.1%)

Site: http://santorini-resto.be/
Report: https://directindex.org/r/santorini-resto.be
Scanned: 2026-10-18 (Provisional: the action test and the assistant citation check still to come; the hatched part of the bar is not measured yet.)
Santorini is mostly ready for agents.
Some AI assistants are turned away by the website of Santorini. It can read what Santorini offers. It finds a way to book or order directly on the site.

## Direct links
- Book directly: https://santorini-resto.be/booking (on the business's own site)
- Order directly: https://santorini-resto.be/food (on the business's own site)
- Menu: https://santorini-resto.be/menu
- Phone: 0485 52 13 38

## What to fix first
- Prices: 30 prices on the site, the middle one €12.75
- Languages: Greek, English, French, Dutch

## What the site tells visitors (Measured, not scored)
- **30 prices on the landing page, the middle one €12.75.** In Brussels, the middle price of comparable sites that show prices is €14.90.

- **The server turns AI crawlers away at the door.** (+10 points) Live fetches as GPTBot (http_403), ClaudeBot (http_403), PerplexityBot (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
- **robots.txt blocks GPTBot, ClaudeBot, Google-Extended, ChatGPT-User, Claude-User, Perplexity-User.** (+7.5 points) These are the crawlers behind ChatGPT, Claude, Perplexity and Google's AI features. Remove the Disallow lines for them, or add explicit Allow rules. Guide: https://directindex.org/guides/robots-txt-for-ai-agents

## Fix kit: What to paste

robots.txt. Add these lines to /robots.txt and delete any Disallow rule that names these crawlers.

```
# Let AI assistants read the site: they send people to you; a marketplace keeps them.
# Remove any Disallow lines for these names elsewhere in this file.
User-agent: GPTBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: Claude-User
Allow: /

User-agent: Perplexity-User
Allow: /
```

## Already right
- **Structured data present (LocalBusiness).** address, phone, opening 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.
- **Ordering on your own site.** Agents can order without a marketplace in the loop.

## Where it stands
487 of 1568 in Brussels. Top 31% 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 | 100% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 100% | no |
| Structured data with address, phone and hours | 94% | yes |
| Have an llms.txt | 3% | yes |

Nearest places in the index: The Noodle Bar (B, 10 m, https://directindex.org/r/noodlebar.be); Hellas (C, 20 m, https://directindex.org/r/pittahellas.be); L'Express (F, 32 m, https://directindex.org/r/lexpress.brussels); Ballekes (C, 42 m, https://directindex.org/r/ballekes.be); Brasserie Auguste (D, 44 m, https://directindex.org/r/brasserie-auguste.be); Papy Burger (A, 47 m, https://directindex.org/r/papyburger.be); Cave du Roy (D, 51 m, https://directindex.org/r/caveduroy.com); 'T Kelderke (A, 54 m, https://directindex.org/r/restaurant-het-kelderke.be); La Rose Blanche (A, 55 m, https://directindex.org/r/restaurant-rose-blanche.be); Waffle Workshop (C, 58 m, https://directindex.org/r/waffleworkshop.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.

Recommended when people ask: "Something to eat after midnight, delivered or open late." (ChatGPT)


See what an AI agent reads on this site: https://directindex.org/r/santorini-resto.be/agent-view

## Named by ChatGPT for "Something to eat after midnight, delivered or open late" in Brussels, October 2026
- "Something to eat after midnight, delivered or open late." (2026-10-15): ChatGPT with a link to this site. https://directindex.org/city/brussels/recommended/late-night
Named by 1 of 2 assistants asked. Badge: https://directindex.org/badge/named/santorini-resto.be.svg

## Businesses like Santorini in Brussels

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Brussels | 1568 | 58% | 36% | 73.1% |

The best of the businesses of the same kind in Brussels: 'T Kelderke (A 100%, https://directindex.org/r/restaurant-het-kelderke.be); 9 et voisins (A 100%, https://directindex.org/r/9-et-voisins.be); A l'Angolo (A 100%, https://directindex.org/r/alangolo.be); Afrikana (A 100%, https://directindex.org/r/afrikanarestaurant.be); Akai (A 100%, https://directindex.org/r/akaibrussels.com).

With the two fixes above (The server turns AI crawlers away at the door; robots.txt blocks GPTBot, ClaudeBot, Google-Extended, ChatGPT-User, Claude-User, Perplexity-User) the score would be about 100%: first of 1,568 in Brussels.

## The direct record
What agents get for Santorini, as JSON: https://directindex.org/api/direct/santorini-resto.be
- Book: https://santorini-resto.be/booking (own site; found by the scan of 2026-10-18, not yet tested)
- Order: https://santorini-resto.be/food (own site; found by the scan of 2026-10-18, not yet tested)
- Menu: https://santorini-resto.be/menu (html_page; from the scan)
- Hours: none on record
- Phone: 0485 52 13 38
- Stable links that count: https://directindex.org/go/santorini-resto.be/book, https://directindex.org/go/santorini-resto.be/order, https://directindex.org/go/santorini-resto.be/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 /menu: menu schema, 112 prices.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 7.5 | 25 |
| Readable | 25 | 25 |
| Actionable | 15 | 15 (the action test: pending) |
| Cited | 0 | 0 (the assistant citation check: pending) |

## Agent readiness (Cloudflare)
Level 2 of 5, Bot-Aware. Cloudflare's report: https://isitagentready.com/santorini-resto.be
- 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: yes
- 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

Keep watching this business (https://directindex.org/r/santorini-resto.be/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/santorini-resto.be/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=santorini-resto.be&force=1