# Robots.txt for https://www.theservicemarketingguys.com
# Policy: all crawlers are welcome on public pages, including search engines,
# answer engines, user-requested fetchers, and model-training crawlers. Only
# private application surfaces are disallowed. Content-Signal is supplemental
# metadata; enforceable crawler access is defined by the User-agent rules.

User-agent: *
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /
Allow: /.well-known/
Allow: /api/mcp
Allow: /api/openapi.json
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/
Disallow: /login
Disallow: /workspace
Disallow: /private/
Disallow: /client/
Disallow: /*.json

# Search, answer engines, user-requested retrieval, and model training
User-agent: Googlebot
User-agent: Google-Extended
User-agent: bingbot
User-agent: OAI-SearchBot
User-agent: ChatGPT-User
User-agent: GPTBot
User-agent: Claude-SearchBot
User-agent: Claude-User
User-agent: ClaudeBot
User-agent: PerplexityBot
User-agent: Perplexity-User
User-agent: Applebot
User-agent: Applebot-Extended
User-agent: Meta-WebIndexer
User-agent: meta-externalfetcher
User-agent: meta-externalagent
User-agent: Amzn-SearchBot
User-agent: Amzn-User
User-agent: Amazonbot
User-agent: MistralAI-Index
User-agent: MistralAI-User
User-agent: MistralAI-Training
User-agent: DuckAssistBot
User-agent: YouBot
User-agent: CCBot
Content-Signal: search=yes, ai-train=yes, ai-input=yes
Allow: /
Allow: /.well-known/
Allow: /api/mcp
Allow: /api/openapi.json
Disallow: /api/
Disallow: /admin/
Disallow: /dashboard/
Disallow: /login
Disallow: /workspace
Disallow: /private/
Disallow: /client/

Sitemap: https://www.theservicemarketingguys.com/sitemap.xml

# Machine-readable site summaries
# https://www.theservicemarketingguys.com/llms.txt
# https://www.theservicemarketingguys.com/llms-full.txt