Agents Index

PublicWWW

OnlineOfficial

Search the source code (HTML, JavaScript, CSS) of web pages.

Visit publisherConnectJSON

What it can do: 11 tools

  • search read-onlyFind websites whose page source (HTML, JavaScript, CSS) contains a string: a library name, a script url, a tracking or widget id, a meta tag, any code fragment. Results are ranked by site popularity. Look a technology up
  • account read-onlyThe account behind the token: the current time (now, UTC), plan, searches used today and left, rate limit, result limits, extraction points left for today (clusters.extract_points_left). Spends nothing. In clusters, max
  • read_docs read-onlyPublicWWW's own documentation and price list, in Markdown: query syntax and operators, websites about a topic (like:), regular expressions (snipexp:), country domains, ready-made example queries, clusters and extraction,
  • list_clusters read-onlyThe account's clusters - saved lists of websites - newest first: id, name, number of domains, creation time. An account keeps at most 100. Spends nothing.
  • get_cluster read-onlyA page of the domains in one cluster. Spends nothing.
  • create_clusterSave a list of websites as a cluster, to extract data from them or combine with other clusters. From a search: pass 'query' (PublicWWW syntax, as in the search tool) - the cluster takes the results up to the plan's limit
  • combine_clustersA new cluster from existing ones: 'and' - domains in every cluster, 'or' - in any of them, 'diff' - the first cluster minus the second (exactly two, order matters): clusters [7, 3] keeps the domains of 7 that are not in
  • extract_from_clusterPull values out of the page source of every website in a cluster: organization names, contacts, social profiles, addresses, languages, registration numbers, analytics and tag ids - anything a regular expression can match
  • build_signatures read-onlyFind signatures that lead to more websites like the ones in a cluster: their common platform, theme, plugin, tracker, network or owner. Each result is a ready search - pass its search (the query in double quotes) to the
  • rename_clusterGive a cluster a new name. Spends nothing.
  • delete_clusterDelete a cluster for good. It cannot be undone - confirm with the user first.

Connect it

Claude Code
claude mcp add --transport http publicwww https://api.publicwww.com/mcp
Claude.ai / ChatGPT
Settings → Connectors → Add custom connector
URL: https://api.publicwww.com/mcp
Cursor (~/.cursor/mcp.json)
{
  "mcpServers": {
    "publicwww": {
      "url": "https://api.publicwww.com/mcp"
    }
  }
}
VS Code (.vscode/mcp.json)
{
  "servers": {
    "publicwww": {
      "type": "http",
      "url": "https://api.publicwww.com/mcp"
    }
  }
}

Questions

What does PublicWWW do?

Search the source code (HTML, JavaScript, CSS) of web pages. It exposes 11 tools to AI assistants.

What tools does PublicWWW provide?

11 tools, including search, account, read_docs, list_clusters, get_cluster, create_cluster, combine_clusters, extract_from_cluster, build_signatures, rename_cluster, delete_cluster.

How do I connect PublicWWW to Claude, ChatGPT or Cursor?

Add the remote MCP endpoint https://api.publicwww.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.

Does PublicWWW require an account or API key?

No sign-in was needed to list its tools. Individual tools may still need an account or API key.

Is PublicWWW online?

As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.

Who publishes PublicWWW?

publicwww.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.

Similar in Web Search & Scraping