# ===============================================================
# robots.txt for m-s-y.com
# Physical file deployment: 2026-04-17
# Reason: avoid LiteSpeed Cache 7-day TTL issue on virtual robots.txt
# Source of truth: Git docs/robots.txt.source -> FTP to webroot
# ===============================================================

# --- Standard WordPress + SEO controls ---
# Block WP search result pages (infinite URL generation, crawl budget waste).
# /wp-includes/ is intentionally NOT blocked: Googlebot needs it for Core Web
# Vitals rendering (CSS/JS assets).
User-agent: *
Disallow: /wp-admin/
Disallow: /*?s=
Disallow: /search/
Allow: /wp-admin/admin-ajax.php

# === AI training data scrapers: BLOCK ===
# Reject large-scale scraping for LLM training data.

User-agent: GPTBot
Disallow: /

User-agent: ClaudeBot
Disallow: /

User-agent: anthropic-ai
Disallow: /

User-agent: claude-web
Disallow: /

User-agent: Google-Extended
Disallow: /

User-agent: Applebot-Extended
Disallow: /

User-agent: CCBot
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: Meta-ExternalAgent
Disallow: /

User-agent: FacebookBot
Disallow: /

User-agent: Diffbot
Disallow: /

User-agent: cohere-ai
Disallow: /

User-agent: Omgilibot
Disallow: /

User-agent: ImagesiftBot
Disallow: /

# === AI search / real-time citation agents: EXPLICITLY ALLOW ===
# Allow retrieval-augmented generation (RAG) and in-browser assistant access.

User-agent: OAI-SearchBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Claude-SearchBot
Allow: /

User-agent: Claude-User
Allow: /

# --- Sitemap ---
Sitemap: https://m-s-y.com/sitemap.xml