User-agent: *
Allow: /
Allow: /docs/
Allow: /help/
Allow: /scan/
Allow: /og/
Allow: /api/og/
Allow: /llm.txt
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Allow: /skill.md
Allow: /auth.md
Allow: /openapi.json
Allow: /docs/skill.md
Allow: /.well-known/skills/
Allow: /.well-known/skills/index.json
Allow: /.well-known/skills/leadmagic
Allow: /.well-known/api-catalog
Allow: /.well-known/agent-skills/
Allow: /.well-known/mcp/
Allow: /.well-known/mcp.json
Allow: /.well-known/mcp/server-card.json
Allow: /docs/.well-known/skills/
Disallow: /api/
Disallow: /scan/api/
Disallow: /scan/admin
Disallow: /admin/
Disallow: /cdn-cgi/
Disallow: /ingest/
Disallow: /_lm/
Disallow: /_g/
Disallow: /lm/ga/
Disallow: /go/

# Search engines and social/link preview crawlers.
User-agent: Googlebot
User-agent: Googlebot-Image
User-agent: Googlebot-News
User-agent: GoogleOther
User-agent: AdsBot-Google
User-agent: AdsBot-Google-Mobile
User-agent: Bingbot
User-agent: DuckDuckBot
User-agent: Applebot
User-agent: Slurp
User-agent: YandexBot
User-agent: Baiduspider
User-agent: LinkedInBot
User-agent: Twitterbot
User-agent: Slackbot-LinkExpanding
User-agent: Discordbot
User-agent: Pinterestbot
User-agent: TelegramBot
User-agent: WhatsApp
User-agent: facebookexternalhit
User-agent: Facebot
Allow: /
Allow: /docs/
Allow: /help/
Allow: /scan/
Allow: /og/
Allow: /api/og/
Disallow: /api/
Disallow: /scan/api/
Disallow: /scan/admin
Disallow: /admin/
Disallow: /cdn-cgi/
Disallow: /ingest/
Disallow: /_lm/
Disallow: /_g/
Disallow: /lm/ga/
Disallow: /go/

# AI search and user-requested retrieval. Allow citation/discovery, not private APIs.
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: MistralAI-User
User-agent: DuckAssistBot
User-agent: Amazonbot
User-agent: Meta-WebIndexer
User-agent: Meta-ExternalFetcher
Allow: /
Allow: /docs/
Allow: /help/
Allow: /scan/
Allow: /llm.txt
Allow: /llms.txt
Allow: /llms-full.txt
Allow: /ai.txt
Allow: /skill.md
Allow: /auth.md
Allow: /openapi.json
Allow: /docs/skill.md
Allow: /.well-known/skills/index.json
Allow: /.well-known/skills/leadmagic
Allow: /.well-known/api-catalog
Allow: /.well-known/agent-skills/
Allow: /.well-known/mcp/
Allow: /.well-known/mcp.json
Allow: /.well-known/mcp/server-card.json
Disallow: /api/
Disallow: /scan/api/
Disallow: /scan/admin
Disallow: /admin/
Disallow: /cdn-cgi/
Disallow: /ingest/
Disallow: /_lm/
Disallow: /_g/
Disallow: /lm/ga/
Disallow: /go/

# Bulk training and high-volume dataset crawlers.
User-agent: GPTBot
User-agent: ClaudeBot
User-agent: Claude-Web
User-agent: Anthropic-AI
User-agent: CCBot
User-agent: Bytespider
User-agent: cohere-ai
User-agent: cohere-training-data-crawler
User-agent: Google-Extended
User-agent: Applebot-Extended
User-agent: Meta-ExternalAgent
User-agent: FacebookBot
User-agent: Diffbot
Disallow: /

# SEO / scrapers, no crawl budget waste.
User-agent: MJ12bot
User-agent: DotBot
User-agent: AhrefsBot
User-agent: SemrushBot
User-agent: BLEXBot
User-agent: DataForSeoBot
User-agent: PetalBot
User-agent: Sogou
Disallow: /

# LLM agent index
# AI crawler policy: https://leadmagic.io/ai.txt
# llms.txt: https://leadmagic.io/llms.txt
# ai.txt: https://leadmagic.io/ai.txt

Sitemap: https://leadmagic.io/sitemap.xml