# Taste Tibet: Agent-Direct Score C (60.9%)

Site: https://www.tastetibet.com/
Report: https://directindex.org/r/tastetibet.com
Scanned: 2026-10-24 (Provisional, with the action test and the assistant citation check still to come. The hatched part of the bar isn't measured yet.)
Taste Tibet is partly visible to agents.
Some AI assistants are turned away by Taste Tibet's website. It can read what Taste Tibet offers. To book or order, it is sent to Deliveroo, a marketplace.

## Direct links
- Menu: https://tastetibet.com/menu/
- Phone: +44 1865 499318
- Address: Magdalen Road 109 OX4 1RQ Oxford
- Hours, from OpenStreetMap: Mon–Tue closed; Wed–Fri 17:00–21:30; Sat–Sun 12:00–15:00, 17:00–21:30
- Its menu mentions: vegan options

## Nearby, also direct
Places near Taste Tibet that take a booking or an order on their own website, with no marketplace in between.
- Elle's Deli & Oli's Thai (60 m): https://directindex.org/r/olisthai.com
- Heat Afro Lounge (370 m): https://directindex.org/r/heatafrolounge.co.uk
- Zakho (380 m): https://directindex.org/r/zakhotakeaway.co.uk
- Pizza Roma (390 m): https://directindex.org/r/pizza-roma.co.uk

## What to fix first
- **Ordering only through deliveroo.** (+12 points) Every transaction an agent makes goes through the marketplace, which takes its commission. Add a direct way on your own site. Even a simple form will do. Guide: https://directindex.org/guides/online-ordering-without-delivery-apps
- **The server turns AI crawlers away at the door.** (+6.7 points) Requests as GPTBot (http_403), ClaudeBot (http_403) were refused, but a normal browser got the page. That's usually a bot list at the host or in a firewall that 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.** (+3.7 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
- **No llms.txt.** (no points, but worth doing) Optional for now and cheap to add. It's a short text file that describes the business for language models. Guide: https://directindex.org/guides/llms-txt-for-a-business

## 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: /
```

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

```
# Taste Tibet

> restaurant (tibetan) in Magdalen Road 109 OX4 1RQ Oxford, Oxford. Phone +44 1865 499318.

## Book or order directly

- Menu: https://tastetibet.com/menu/

## Opening hours

We-Fr 17:00-21:30; Sa,Su 12:00-15:00, 17:00-21:30

## About

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

## Already right
- **Structured data found (Restaurant).** address, phone, opening hours
- **Menu or price list is an HTML page.** Agents can read the items and prices.

## Where it stands
151 of 217 in Oxford. Top 70% of the sites scanned in this index.

| What the top 10% 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 | 100% | yes |
| Let AI crawlers in (no block at the server or in robots.txt) | 100% | no |
| Structured data with address, phone and hours | 64% | yes |
| Have an llms.txt | 23% | no |

Nearest places in the index: Elle's Deli & Oli's Thai (D, 63 m, https://directindex.org/r/olisthai.com); Everest Nepalese Restaurant And Bar (D, 306 m, https://directindex.org/r/everest-nepalese.co.uk); Heat Afro Lounge (A, 374 m, https://directindex.org/r/heatafrolounge.co.uk); Sir Sun's Wok (D, 374 m, https://directindex.org/r/sirsunswokoxford.co.uk); Dollar Burger (F, 375 m, https://directindex.org/r/dollarburgers.co.uk); Sunny (D, 376 m, https://directindex.org/r/sunnichinesetakeaway.co.uk); Zakho (C, 384 m, https://directindex.org/r/zakhotakeaway.co.uk); Pepe's (B, 386 m, https://directindex.org/r/pepes.co.uk); Pizza Roma (A, 387 m, https://directindex.org/r/pizza-roma.co.uk); Exprizza And Desi Grill (D, 391 m, https://directindex.org/r/express-pizza-desi-grill.co.uk).

## What assistants answer
The assistants haven't been asked about this business yet. They're asked about the top-ranked businesses in each city index, and about any business as soon as it's claimed. Claim this page to be included.

The assistants were asked 22 everyday questions about Oxford and named 87 places. Taste Tibet wasn't one of them. See who was named: https://directindex.org/city/oxford/recommended


Compared with its peers: Sites built with WordPress 55% (24% A or B, 224455 sites); Sites using Deliveroo 63% (38% A or B, 798 sites); This site 60.9%.

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

## Businesses like Taste Tibet in Oxford

| Group | Sites | Avg score | A or B | This site |
|---|---|---|---|---|
| Businesses of the same kind in Oxford | 217 | 68% | 55% | 60.9% |
| Sites built with WordPress in Oxford | 62 | 73% | 63% | 60.9% |
| Sites using Deliveroo in Oxford | 14 | 63% | 43% | 60.9% |
| Sites built with WordPress and using Deliveroo in Oxford | 4 | 72% | 75% | 60.9% |

The best of the sites built with WordPress and using Deliveroo in Oxford: Cuttlefish (B 76.9%, https://directindex.org/r/cuttlefishoxford.co.uk); La Cucina (B 76.9%, https://directindex.org/r/lacucinaoxford.co.uk); Sichuan Grand (B 72.3%, https://directindex.org/r/sichuangrand.com).

With the three fixes above (Ordering only through deliveroo; The server turns AI crawlers away at the door; robots.txt blocks GPTBot, ClaudeBot, Google-Extended), the score would be about 95.4%. That would be 10th of 217 in Oxford, up from 151st.

This site appears in 2 cities (2 places on tastetibet.com). https://directindex.org/brand/tastetibet.com

## The direct record
What agents get for Taste Tibet, as JSON: https://directindex.org/api/direct/tastetibet.com
- Book: none on record
- Order: none on record
- Menu: https://tastetibet.com/menu/ (html_page; from the scan)
- Hours: We-Fr 17:00-21:30; Sa,Su 12:00-15:00, 17:00-21:30 (closed now) (from OpenStreetMap)
- Phone: +44 1865 499318
- Stable links that count: https://directindex.org/go/tastetibet.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): 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): yes
- Ordering vendor that takes agent orders (Square, Toast, or a vendor whose terms allow agents): no
- Vendor terms for agents, Deliveroo: Not stated. Deliveroo's terms of service (6 October 2026) and terms of use say nothing about bots or automated ordering; they bar access without authority and interference with the service; no agent programme was found. Read 2026-10-15: https://deliveroo.co.uk/legal

Found one hop past the home page: menu page /menu/: ordering via deliveroo.

## Score breakdown
| Component | Points | Available |
|---|---|---|
| Reachable | 14.6 | 25 |
| Readable | 22 | 25 |
| Actionable | 3 | 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/tastetibet.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: yes
- 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: yes
- A2A agent card: no (how: https://isitagentready.com/.well-known/agent-skills/a2a-agent-card/SKILL.md)
- Agent Skills index: yes
- 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

Keep watching this business (https://directindex.org/r/tastetibet.com/plan): the assistants are asked again every month, and you see what changed. 2 EUR a month or 19 EUR a year.
Deep report: https://directindex.org/r/tastetibet.com/deep. Ten questions phrased the way people ask them, each assistant's full answer, the eight nearest similar places, the fix plan and a PDF. 5 EUR, paid once. 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=tastetibet.com&force=1