# ================================
# Mission Disrupt - robots.txt
# ================================

# ----------------
# Global rules
# ----------------
User-agent: *
Disallow: /wp-admin/
Disallow: /wp-includes/
Disallow: /wp-content/plugins/
Disallow: /wp-content/cache/
Disallow: /readme.html
Disallow: /license.txt
Allow: /wp-admin/admin-ajax.php

# ----------------
# Allow well-known AI & search bots
# ----------------
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Googlebot-News
Allow: /

User-agent: Bingbot
Allow: /

User-agent: Applebot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

# AI / LLM crawlers (allowed)
User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: PerplexityAI
Allow: /

# ----------------
# Block scraping & aggressive bots
# ----------------
User-agent: AhrefsBot
Disallow: /

User-agent: SemrushBot
Disallow: /

User-agent: MJ12bot
Disallow: /

User-agent: DotBot
Disallow: /

User-agent: BLEXBot
Disallow: /

User-agent: PetalBot
Disallow: /

User-agent: DataForSeoBot
Disallow: /

User-agent: Scrapy
Disallow: /

User-agent: Crawler4j
Disallow: /

User-agent: Bytespider
Disallow: /

User-agent: GPTBot-User
Disallow: /

# ----------------
# Sitemap
# ----------------
Sitemap: https://www.missiondisrupt.com/sitemap_index.xml