# Maventech — robots.txt
# Dynamically generated from https://maventechsoftware.com at 2026-09-07T21:06:08+00:00.
# Edit /robots-txt.php to change the rules; this file is served from /robots.txt.

# ----- Default policy for all crawlers -----
User-agent: *
Allow: /
# Content Signals — declare how automated clients may use content fetched here
# (Cloudflare / IETF "Content-Signal" convention). search + AI answers with
# citation are welcome; using our content to TRAIN models is not permitted.
Content-Signal: search=yes, ai-input=yes, ai-train=no
Disallow: /admin.php
Disallow: /admin-email-preview.php
Disallow: /logout.php
Disallow: /email-view.php
Disallow: /email-api.php
Disallow: /uploads/order-pdfs/
Disallow: /cron.php
Disallow: /setup-check.php
Disallow: /*?session_id=
Disallow: /*?order=
Disallow: /wp-admin/
Disallow: /wp-content/
Disallow: /wp-includes/
Disallow: /wp-login.php
Disallow: /wp-cron.php
Disallow: /xmlrpc.php
Disallow: /cgi-bin/
Disallow: /feed/
Disallow: /comments/feed/
Disallow: /*/feed/
Disallow: /*?add-to-cart=

# ----- Explicit allow-list for search + AI crawlers (no rate limit) -----
User-agent: Googlebot
Allow: /

User-agent: Googlebot-Image
Allow: /

User-agent: Bingbot
Allow: /

User-agent: DuckDuckBot
Allow: /

User-agent: Slurp
Allow: /

User-agent: YandexBot
Allow: /

User-agent: Baiduspider
Allow: /

User-agent: GPTBot
Allow: /

User-agent: ChatGPT-User
Allow: /

User-agent: OAI-SearchBot
Allow: /

User-agent: anthropic-ai
Allow: /

User-agent: ClaudeBot
Allow: /

User-agent: Claude-Web
Allow: /

User-agent: PerplexityBot
Allow: /

User-agent: Perplexity-User
Allow: /

User-agent: Google-Extended
Allow: /

User-agent: DeepSeekBot
Allow: /

User-agent: DeepSeek
Allow: /

User-agent: Applebot
Allow: /

User-agent: Applebot-Extended
Allow: /

User-agent: cohere-ai
Allow: /

User-agent: Bytespider
Allow: /

User-agent: DiffBot
Allow: /

User-agent: FacebookExternalHit
Allow: /

User-agent: Amazonbot
Allow: /

User-agent: meta-externalagent
Allow: /

User-agent: YouBot
Allow: /

User-agent: PhindBot
Allow: /

User-agent: KagiBot
Allow: /

User-agent: MistralAI-User
Allow: /

User-agent: CCBot
Allow: /

User-agent: PetalBot
Allow: /

User-agent: Brave-Search
Allow: /

User-agent: NeevaBot
Allow: /

User-agent: Andibot
Allow: /


# ----- Sitemap (auto-resolves to the live host) -----
# Only a valid XML sitemap (<urlset>/<sitemapindex>) belongs here. The product
# feeds are RSS Merchant feeds (submit them in Google Merchant Center / Bing,
# not as a Sitemap) and llms.txt / agents.json are AI-crawler files — listing
# any of these as "Sitemap:" makes Search Console report an unsupported format.
Sitemap: https://maventechsoftware.com/sitemap.xml

# Non-sitemap resources (discovery only — NOT submitted as sitemaps):
#   Google Merchant feed : https://maventechsoftware.com/merchant-feed.xml
#   Bing shopping feed   : https://maventechsoftware.com/feed/bing-shopping.xml
#   AI guidance          : https://maventechsoftware.com/llms.txt , https://maventechsoftware.com/agents.json
#   AI full context      : https://maventechsoftware.com/llms-full.txt (inlined catalog + policies + guides + FAQs)
#   Developer / API docs  : https://maventechsoftware.com/developers , https://maventechsoftware.com/openapi.json , https://maventechsoftware.com/api
#   Agent instructions   : https://maventechsoftware.com/AGENTS.md (when-to-use guidance)