PublicWWW
Search web page source code for scripts, libraries and tracking IDs from an AI assistant
- Pricing
- Paid
- Platforms
- Web, API
- Runs
- Remotely
- Version
- 1.3.0
- Listing updated
- 3 days ago
About PublicWWW
PublicWWW is a paid MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
PublicWWW indexes the HTML, JavaScript and CSS of web pages, and this remote server hands that search to an assistant. Ask which sites load a given script, use a library or carry a tracking ID, and the assistant writes the query in PublicWWW's syntax and returns the matching sites, optionally with fragments of their source.
Beyond single searches there are eight cluster tools. A cluster is a saved list of sites that the assistant can build, combine, extract data from (contacts, social profiles, tag IDs) and analyse for shared signatures. A separate account tool reports the plan and remaining daily searches, and read_docs returns the documentation and price list.
Access needs a paid plan: free accounts can connect but most calls are refused with plan_required. The tool list and docs can be read without signing in. Daily searches are shared with the REST API and the website.
Install
Run in a terminal
claude mcp add --transport http publicwww https://api.publicwww.com/mcpAdd to Settings → Connectors → Add custom connector
https://api.publicwww.com/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"publicwww": {
"url": "https://api.publicwww.com/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"publicwww": {
"type": "http",
"url": "https://api.publicwww.com/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"publicwww": {
"serverUrl": "https://api.publicwww.com/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"publicwww": {
"type": "http",
"url": "https://api.publicwww.com/mcp"
}
}
}Tools this server provides (3)
Taken from the project documentation; the running server may differ.
- search
- Runs a query and returns matching sites, with source fragments if asked.
- account
- Shows plan and searches and extraction points left today.
- read_docs
- Returns PublicWWW documentation and the price list.
What it does
- Source-code search
- Runs PublicWWW queries and returns sites with optional code snippets.
- Cluster building
- Saves, combines and extracts data from lists of sites.
- Quota check
- Reports plan and searches left today.
- Documentation tool
- Reads the docs and price list from inside the chat.
- OAuth or token sign-in
- Claude and ChatGPT use OAuth; other clients send a bearer token.
- Client plugins
- Ships configs for Cursor, VS Code, Gemini CLI, Codex and more.
Good for
- Find every site loading a specific script
- Build a prospect list of sites using a given widget
- Pull contact emails from a cluster of matching sites
- Check competitors' tag manager and analytics usage
Pricing
Paid
Requires a paid PublicWWW plan; prices not published here.
Prices change. Check publicwww.com before you buy.
PublicWWW FAQ
Do I need a paid plan?
Yes; free accounts are refused with plan_required except for account and read_docs.
How do I sign in?
OAuth in Claude, ChatGPT and Claude Code, or a token from your profile page in a bearer header.
What is the endpoint?
https://api.publicwww.com/mcp.
Are quotas shared?
Yes, daily searches are shared with the API and the website.
Is PublicWWW free?
No. PublicWWW is a paid product.
How do I add PublicWWW to Claude Code?
Run this command in your terminal: claude mcp add --transport http publicwww https://api.publicwww.com/mcp
What are the best alternatives to PublicWWW?
The closest alternatives to PublicWWW are Scrapling MCP Server, Firecrawl MCP Server, Google Ads + Meta Ads + SEO/GEO MCP, SearXNG Search and Calven.
Alternatives to PublicWWW

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

Google Ads + Meta Ads + SEO/GEO MCP
MCP serverHosted MCP connector for managing Google Ads, Meta Ads, GA4 and Search Console from chat
- 8 tools
- Remote
- Freemium
- 8.1K GitHub stars
- Marketing and SEO

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

Calven
MCP serverProduct marketing context from Calven delivered into Claude, ChatGPT and other AI tools
Not checked yet- Remote
- Free trial
- 3 GitHub stars
- Marketing and SEO

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping