MCP ExplorerExplorer

Remote Mcp Server Authless Scrape And Analyze Website

@elizabethsiegleon 10 months ago
6 MIT
FreeCommunity
AI Systems
#browser-rendering#cloudflare#cloudflare-browser-rendering#cloudflare-workers#cloudflare-workers-ai#cloudflareworkers#mcp#workers-ai#workersai
Analyze and ask questions about an input website using this Cloudflare MCP server

Overview

What is Remote Mcp Server Authless Scrape And Analyze Website

remote-mcp-server-authless-scrape-and-analyze-website is a Cloudflare MCP server that allows users to analyze and ask questions about any input website without requiring authentication. It leverages Cloudflare’s browser rendering and AI capabilities for content extraction and analysis.

Use cases

Use cases include analyzing competitor websites for insights, summarizing content for quick reviews, and answering specific queries about a website’s offerings or services.

How to use

To use the remote MCP server, you can deploy it to Cloudflare Workers via the provided deployment link or by using the command line. After deployment, you can access the server at a URL like ‘remote-mcp-server-authless..workers.dev/sse’. You can then utilize tools like ‘analyze_website’ and ‘ask_q_about_website’ to analyze websites and ask questions.

Key features

Key features include the ability to scrape and analyze websites using Cloudflare’s browser rendering, generate summaries of website content, and answer specific questions about the website using AI.

Where to use

This MCP server can be used in various fields such as web development, digital marketing, content analysis, and research, where understanding website content is essential.

Content

Building a Remote MCP Server on Cloudflare (Without Auth)

This example allows you to deploy a remote MCP server that doesn’t require authentication on Cloudflare Workers. The server includes tools for website analysis and content extraction using Cloudflare’s Browser Rendering and AI capabilities.
example image

Get started:

Deploy to Workers

This will deploy your MCP server to a URL like: remote-mcp-server-authless.<your-account>.workers.dev/sse

Alternatively, you can use the command line below to get the remote MCP Server created on your local machine:

npm create cloudflare@latest -- my-mcp-server --template=cloudflare/ai/demos/remote-mcp-authless

Available Tools

Website Analysis Tools

  1. analyze_website

    • Scrapes and analyzes a website using Cloudflare’s browser rendering
    • Uses Cloudflare AI to provide a summary of the website’s content
    • Input: url (string) - The website URL to analyze
    • Example: [tool] analyze_website(url: "https://example.com")
  2. ask_q_about_website

    • Scrapes a website and answers specific questions about its content
    • Uses Cloudflare AI to understand and respond to questions about the website
    • Inputs:
      • url (string) - The website URL to analyze
      • question (string) - Your question about the website content
    • Example: [tool] ask_q_about_website(url: "https://example.com", question: "What services does this company offer?")

Customizing your MCP Server

To add your own tools to the MCP server, define each tool inside the init() method of src/index.ts using this.server.tool(...).

Connect to Cloudflare AI Playground

You can connect to your MCP server from the Cloudflare AI Playground, which is a remote MCP client:

  1. Go to https://playground.ai.cloudflare.com/
  2. Enter your deployed MCP server URL (remote-mcp-server-authless.<your-account>.workers.dev/sse)
  3. You can now use your MCP tools directly from the playground!

Connect Claude Desktop to your MCP server

You can also connect to your remote MCP server from local MCP clients, by using the mcp-remote proxy.

To connect to your MCP server from Claude Desktop, follow Anthropic’s Quickstart and within Claude Desktop go to Settings > Developer > Edit Config.

Update with this configuration:

Restart Claude and you should see the tools become available.

Requirements

To use the website analysis tools, you need:

  1. Cloudflare Workers with browser binding enabled
  2. Cloudflare AI binding configured
  3. Appropriate permissions for both bindings

Make sure your wrangler.jsonc includes:

{
  "browser": {
    "binding": "BROWSER"
  },
  "ai": {
    "binding": "AI"
  }
}

Tools

No tools

Comments

Recommend MCP Servers

View All MCP Servers