Content-Signal: ai-train=no, search=yes, ai-input=yes

# robots.txt for Tool Index (https://toolindex.net)
# Content-Signal above declares default AI usage preferences per
# https://contentsignals.org/. Search indexing and AI inference are welcome;
# bulk model training is not.

User-agent: *
Content-Signal: ai-train=no, search=yes, ai-input=yes
Allow: /

# Block private routes
Disallow: /admin/
Disallow: /api/
Disallow: /auth/
Disallow: /dashboard/
Disallow: /go/

# Useful pagination and public parameter variants stay crawlable so crawlers
# can follow ordinary page links and observe route-level canonical/noindex tags.
Crawl-delay: 1

# Sitemap location (absolute URL)
Sitemap: https://toolindex.net/sitemap.xml

# ARD capability manifest (agenticresourcediscovery.org)
Agentmap: https://toolindex.net/.well-known/ai-catalog.json

# Agent discovery (RFC 8288, RFC 9727, agentskills.io)
# Catalog of well-known endpoints agents can probe to bootstrap automation:
#   - /.well-known/api-catalog
#   - /.well-known/agent-skills/index.json
#   - /.well-known/mcp/server-card.json
#   - /.well-known/oauth-protected-resource
#   - /.well-known/ai-catalog.json
#   - /auth.md
# Tool/blog detail pages also serve text/markdown when requested via
# Accept: text/markdown or ?format=md.
# A plain-text guide for AI assistants (llmstxt.org): /llms.txt