oxylabs.io agentic web readiness

A Manifest validity: 100% (3/3 valid, 0 errors, 6 warnings) · Surface score 51 (coverage 30 + breadth 6 + conformance 15). 4 standards observed across 3 of 9 steps; 3 manifests present, 0 errors, 6 warnings. Checked 2026-10-25 23:11:46 UTC. This grades the agent-facing files published at oxylabs.io, not the organisation's products.

Badge for a README: ![agentic web grade](https://agenticweb.wiki/badge/oxylabs.io.svg) · JSON · Markdown · Re-check now

Coverage by step

Manifests

What an agent can call

• llms.txt: Oxylabs, 48 links
• robots.txt AI policy: allows GPTBot, OAI-SearchBot, ChatGPT-User, ClaudeBot, Claude-User, Claude-SearchBot, anthropic-ai, Google-Extended, PerplexityBot, Perplexity-User, CCBot, Applebot-Extended, meta-externalagent, Bytespider, Amazonbot, cohere-ai, DuckAssistBot, MistralAI-User; unlisted crawlers allowed
• ARD bridge (/.well-known/ai-catalog.json): 0/1 valid, 0 legacy, 0 dead/broken (served at deprecated path only)

Standards observed

• llms.txt https://oxylabs.io/llms.txt
• Content Signals Policy https://oxylabs.io/robots.txt
• AI Catalog well-known file https://oxylabs.io/.well-known/ai-catalog.json
• AI Crawler User-Agent Tokens in robots.txt https://oxylabs.io/robots.txt

Cheapest next steps

1. Agentic Resource Discovery: a catalog at /.well-known/ard.json lets agents discover your APIs, MCP servers and data in one fetch (emerging spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "ard", "domain": "oxylabs.io"}))
2. AGENTS.md: instructions for coding agents working on or with the site
   Generate starter /AGENTS.md for oxylabs.io

   # Oxylabs for agents
   
   Oxylabs and what it offers to agents
   
   ## Read the data, not the HTML
   - Index: https://oxylabs.io/llms.txt
   - API description: https://oxylabs.io/openapi.json
   - Discovery catalog: https://oxylabs.io/.well-known/ard.json
   
   ## Calling
   - MCP server (Streamable HTTP): https://oxylabs.io/mcp
   - Rate limits and authentication: describe them here
   
   ## Conventions
   - How to cite or attribute content
   - What not to do (no scraping of /account/, no automated sign-ups, etc.)
   
   Contact: security@oxylabs.io
   

3. api-catalog: A Well-Known URI and Link Relation to Help Discovery of APIs: an RFC 9727 linkset pointing at your OpenAPI description (conditional spec — publish only if you run the underlying endpoints; generate via MCP template({"id": "api-catalog-rfc9727", "domain": "oxylabs.io"}))

Agent pre-flight & practical readiness

Preferred mode: llms_txt. GET /llms.txt and follow the links it names. That index is the page list an agent should read.

Fetch: GET https://oxylabs.io/llms.txt GET /llms.txt and follow its links.

Practical readability: exa_parsable no, markdown negotiation no, render blocked, HTML quality blocked.

AI crawler posture: waf_challenged · Assistant access: OpenAI blocked, Anthropic blocked, Google blocked, Perplexity blocked, Exa blocked.

Readiness subscores: reach 4/20, readability 0/30, capabilities 7/35, conformance 15/15, total 26/100, grade D.

How the grade is made

+10 per lifecycle step with a standard observed, counting manifests that validate or that the probe rule for the standard recognises (a valid MCP server card counts for MCP; max 90); +3 per observed standard beyond the first two (max 15); conformance +15 (+10 with one manifest) minus 5 per agent-facing manifest with errors, never below 0 (security.txt is reported, not scored). Lifecycle grade: A+ >= 60, A >= 45, B >= 30, C >= 20, D >= 10. Strict 100-point composite (subscores.total_100 / subscores.grade_100): reach_and_policy (20) + readability (30) + capabilities (35) + conformance (15), where A+ >= 80, A >= 65, B >= 45, C >= 28, D >= 15. Errors are specification violations; warnings are best-practice gaps. Only public paths are fetched, without credentials, so standards that need a login (skipped in the probe) are not counted either way. The same report is the validate_manifest tool on the MCP server.

JSON · Markdown · probe rules