# Café Obrkof: Agent-Direct Score B (81.5%)

Site: https://www.obrkof.com
Report: https://directindex.org/r/obrkof.com
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.)
Café Obrkof is mostly ready for agents.

## Direct links
- Menu: https://obrkof.com/#carte
- Phone: +33674570990

## 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
- **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

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

```
# Café Obrkof

> cafe or coffee shop in Paris cafes and bars. Phone +33674570990.

## Book or order directly

- Menu: https://obrkof.com/#carte

## About

- Website: https://www.obrkof.com
- 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 (CafeOrCoffeeShop).** address, phone, opening hours
- **Menu or price list is an HTML page.** Agents can read items and prices directly.
- **Uber Eats lets agents act only 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 cannot finish the step there; a direct path on your own domain works for all of them.

## Where it stands
114 of 806 in Paris cafes and bars. Top 14% 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 | 99% | no |
| Publish the menu or price list as HTML | 91% | yes |
| Let AI crawlers in (no edge block, no robots.txt block) | 100% | yes |
| Structured data with address, phone and hours | 56% | yes |
| Have an llms.txt | 41% | no |

Nearest places in the index: Les BerthoM (C, 50 m, https://directindex.org/r/lesberthom.com); Kapé (C, 73 m, https://directindex.org/r/kapeparis.com); Rock Star Café (F, 119 m, https://directindex.org/r/aperockcafe.com); Le Mammouth (B, 191 m, https://directindex.org/r/lemammouth-bar.fr); Off : campus (C, 224 m, https://directindex.org/r/offcampus.fr); Paris Féni (D, 271 m, https://directindex.org/r/parisfeni.com); Martin - Boire & manger (F, 274 m, https://directindex.org/r/bar-martin.fr); La Loutre Bar (D, 293 m, https://directindex.org/r/animaux.bar); L'Orée Café (C, 328 m, https://directindex.org/r/loreecafe.com); Dirty Lemon (B, 329 m, https://directindex.org/r/dirtylemonbar.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 using Uber Eats 63% (34% A or B, 659 sites); This site 81.5%.

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

## Businesses like Café Obrkof in Paris cafes and bars

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Same kind in Paris cafes and bars | 806 | 54% | 31% | 81.5% |
| Using Uber Eats in Paris cafes and bars | 8 | 66% | 38% | 81.5% |

The best of Using Uber Eats in Paris cafes and bars: Proost (B 76.9%, https://directindex.org/r/proost.fr); Le Village (B 72.3%, https://directindex.org/r/levillagebistrot.fr); Le Petit Marcel (C 67.2%, https://directindex.org/r/lepetitmarcelparis.fr); Wild & The Moon (C 66.2%, https://directindex.org/r/wildandthemoon.fr); Kafkaf (C 61.5%, https://directindex.org/r/thehungryfamily.com).

With the fix above (Ordering only through ubereats) the score would be about 100%: first of 806 in Paris cafes and bars.

## The direct record
What agents get for Café Obrkof, as JSON: https://directindex.org/api/direct/obrkof.com
- Book: none on record
- Order: none on record
- Menu: https://obrkof.com/#carte (html_page; from the scan)
- Hours: none on record
- Phone: +33674570990
- Stable links that count: https://directindex.org/go/obrkof.com/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: Partners only. 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 | 25 | 25 |
| Readable | 25 | 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/obrkof.com
- 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: yes
- 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/obrkof.com/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=obrkof.com&force=1