Search indexed website HTML, JavaScript and CSS with PublicWWW MCP, and inspect account search limits through its read-only tools.
PublicWWW MCP searches PublicWWW’s index of website source code. It is useful for finding pages that contain a script identifier, HTML fragment, CSS pattern or another code-level signature.
Use a specific identifier rather than a broad product name when investigating a technology footprint. Request snippets with the results so you can see why a page matched. An indexed match reflects the provider’s stored crawl data; inspect the live page before treating the code as currently present.
The hosted endpoint is https://api.publicwww.com/mcp. PublicWWW documents OAuth and token authentication using PUBLICWWW_TOKEN. Its two read-only tools are search and account. Plans have search allowances, so use the account result to understand the available capacity before a larger research task.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| search | Search indexed website source code, with pagination and snippets. |
| account | Inspect the plan and remaining searches. |
claude mcp add --transport http publicwww https://api.publicwww.com/mcpComplete the provider sign-in flow in a client that supports HTTP and OAuth.
A PublicWWW account and the documented OAuth or token connection. Search limits depend on the account plan.
Retrieve public web pages as readable Markdown with the reference Fetch MCP server, including pagination for longer responses.
Use Firecrawl MCP to retrieve website content and extract information for research through Firecrawl’s API-backed web tools.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.