Skip to content

Use cases

What people feed the rat.

Each one is a workflow on the same API: one key, one credit balance, failed pages free.

Chatbots and RAG

Crawl a site into clean, token-counted chunks. Boilerplate removed site-wide, so your bot answers from content, not the footer.

  1. crawl
  2. chunks
  3. embed
  4. answer
request
curl -X POST "https://api.vermin.dev/v1/crawl" \
  -H "Authorization: Bearer $VERMIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "url": "https://docs.example.com",
    "limit": 500,
    "scrapeOptions": { "formats": ["chunks"] }
  }'

AI agents

Give an agent reliable reading glasses. Every endpoint is an MCP tool.

  1. agent
  2. map
  3. scrape
  4. answer
request
claude mcp add --transport http vermin https://mcp.vermin.dev/mcp

Monitoring

Scrape pages from your own scheduler and diff the markdown. Failed checks cost nothing.

  1. cron
  2. scrape
  3. diff
  4. alert
request
curl -X POST "https://api.vermin.dev/v1/scrape" \
  -H "Authorization: Bearer $VERMIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://competitor.example/pricing", "formats": ["markdown"] }'

Brand enrichment

Turn a domain into a logo, colours and fonts for onboarding, CRMs or white-labelled UIs.

  1. domain
  2. brand
  3. your UI
request
curl "https://api.vermin.dev/v1/brand?domain=stripe.com" \
  -H "Authorization: Bearer $VERMIN_API_KEY"

Site discovery

List every URL on a site before you decide what to crawl.

  1. map
  2. filter
  3. crawl
request
curl -X POST "https://api.vermin.dev/v1/map" \
  -H "Authorization: Bearer $VERMIN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "url": "https://shop.example", "search": "product", "limit": 1000 }'

Pick a job. Start here.

Start building Read the docs