Enables source-code searches for sites using Angular, such as pages containing angular.min.js, and clustering matching sites.
Extraction preset pulls Bluesky profile links or handles from the source of clustered sites.
Enables source-code searches for sites using Bootstrap and saving matching sites as clusters.
Extraction preset pulls Discord invite or profile links from site source.
Extraction preset pulls Facebook page or profile links from site source.
Extraction preset pulls GitHub profile or repository links from site source.
Supports finding sites that load the Hotjar tracking script, such as static.hotjar.com, and saving them as clusters.
Extraction preset pulls Instagram profile links from site source.
Enables source-code searches for sites using jQuery, including combined conditions with other libraries.
Extraction preset pulls LINE contact or profile links from site source.
Extraction preset pulls Pinterest profile links from site source.
Enables source-code searches for sites using Swiper and clustering matching sites.
Extraction preset pulls Telegram usernames or links from site source.
Extraction preset pulls Threads profile links from site source.
Extraction preset pulls TikTok profile links from site source.
Extraction preset pulls Viber contact links or identifiers from site source.
Extraction preset pulls WhatsApp contact links or numbers from site source.
Extraction preset pulls YouTube channel or video links from site source.
This server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
Search the source code (HTML, JavaScript, CSS) of web pages from an AI assistant: which sites load a script, use a library, carry a tracking id or a widget - then save them as a cluster and pull contacts, social profiles or tag ids out of their pages. PublicWWW runs a remote MCP server:
https://api.publicwww.com/mcpTools: search (query, rows, page, snippets), account (plan, searches and
extraction points left today), read_docs (PublicWWW's own documentation and price
list in Markdown) and eight for clusters. The same documentation pages
are MCP resources, publicwww://docs/<page>. Without signing in, the tool list and
read_docs work; the other tools need a paid plan, and a free account gets
plan_required from them - see
limits.
OAuth - Claude, ChatGPT and Claude Code send you to PublicWWW to press Allow. Nothing to copy.
A token - other clients send Authorization: Bearer <token>. Issue one on your
profile page and keep it in the
PUBLICWWW_TOKEN environment variable.
Related MCP server: Prospect Research MCP Server
Client | How |
Claude (web, desktop) | Customize → Connectors → Add custom connector, URL above - guide |
ChatGPT | Plugins → Add → Add custom MCP server, OAuth - guide |
Claude Code | the plugin below, or |
Cursor |
|
VS Code | |
Gemini CLI |
|
Codex CLI |
|
opencode | |
Goose | |
Qwen Code | |
DeepSeek Harness |
|
Anything else | a config file from |
The Cursor button reads the token from PUBLICWWW_TOKEN; VS Code asks for it once
and keeps it in its secret storage.
The MCP server (sign in with OAuth) and a skill that teaches the query syntax:
/plugin marketplace add publicwww-com/publicwww-mcp
/plugin install publicwww@publicwwwThen run /mcp, pick publicwww and choose Authenticate.
gemini extensions install https://github.com/publicwww-com/publicwww-mcpIt asks for the token once and keeps it in the system keychain.
skills/publicwww-search is a skill in the open
Agent Skills format: how to write PublicWWW queries and use the tools. Copy the
folder into your agent's skills directory (for example .agents/skills/ or
~/.claude/skills/).
skills/publicwww-api does the same for the
REST API, for agents that call it from code or the shell.
Query | Finds |
| that exact text in the page source |
| both, anywhere on the page |
| jquery and either of the two |
| the first without the second |
| only .de sites |
| inner pages too, not only home pages |
More: query syntax.
A cluster is a saved list of websites the assistant can build, combine and extract data from.
Tool | What it does |
| the account's clusters, newest first |
| a page of the domains in a cluster |
| from a search ( |
|
|
| values from the page source of every site: ready-made |
| a new name |
| deletes for good; marked destructive, so the assistant asks you first |
Presets: email, phone, whatsapp, telegram, viber, line, facebook,
instagram, x, linkedin, youtube, tiktok, pinterest, threads, bluesky,
discord, github, google_play, app_store. Anything else
is a regular expression in slashes whose first group is the value, e.g.
/data-site-id="([0-9]+)"/i. Extraction spends the day's extraction points; an
account keeps up to 100 clusters.
Ask in plain words: "Find sites that load static.hotjar.com, save them as a cluster
and get their contact emails and phones" - the assistant runs create_cluster,
then extract_from_cluster with the email and phone presets until the cluster
is done. More: tools.
examples/mcp-curl.sh lists the tools, reads the account and
runs a search with plain curl. Streamable HTTP, JSON answers, no sessions - see
for developers.
For scripts the REST API is the simpler road - the same search, clusters and token, with CSV and NDJSON. Small clients: Python, JavaScript, PHP, Go, Ruby.
MIT
This server cannot be deployed
Search websites by source code, technology stack, analyze domains, and download lead lists.
Web scraping, search, crawling, structured extraction and research for AI agents.
Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summary
Extracts verified emails, social links, 40+ tech stack signals, pricing tiers, and company summar.
