MCP Webscan Server

A Model Context Protocol (MCP) server for web content scanning and analysis. This server provides tools for fetching, analyzing, and extracting information from web pages.

Features

Page Fetching: Convert web pages to Markdown for easy analysis
Link Extraction: Extract and analyze links from web pages
Site Crawling: Recursively crawl websites to discover content
Link Checking: Identify broken links on web pages
Pattern Matching: Find URLs matching specific patterns
Sitemap Generation: Generate XML sitemaps for websites

Installation

Installing via Smithery

To install Webscan for Claude Desktop automatically via Smithery:

npx -y @smithery/cli install mcp-server-webscan --client claude

Manual Installation

# Clone the repository
git clone <repository-url>
cd mcp-server-webscan

# Install dependencies
npm install

# Build the project
npm run build

Usage

Starting the Server

npm start

The server runs on stdio transport, making it compatible with MCP clients like Claude Desktop.

Available Tools

fetch_page
- Fetches a web page and converts it to Markdown
- Parameters:
  - url (required): URL of the page to fetch
  - selector (optional): CSS selector to target specific content
extract_links
- Extracts all links from a web page with their text
- Parameters:
  - url (required): URL of the page to analyze
  - baseUrl (optional): Base URL to filter links
crawl_site
- Recursively crawls a website up to a specified depth
- Parameters:
  - url (required): Starting URL to crawl
  - maxDepth (optional, default: 2): Maximum crawl depth
check_links
- Checks for broken links on a page
- Parameters:
  - url (required): URL to check links for
find_patterns
- Finds URLs matching a specific pattern
- Parameters:
  - url (required): URL to search in
  - pattern (required): Regex pattern to match URLs against
generate_sitemap
- Generates a simple XML sitemap
- Parameters:
  - url (required): Root URL for sitemap
  - maxUrls (optional, default: 100): Maximum number of URLs to include

Example Usage with Claude Desktop

Configure the server in your Claude Desktop settings:

{
  "mcpServers": {
    "webscan": {
      "command": "node",
      "args": ["path/to/mcp-server-webscan/dist/index.js"],
      "env": {
        "NODE_ENV": "development"
      }
    }
  }
}

Use the tools in your conversations:

Could you fetch the content from https://example.com and convert it to Markdown?

Development

Prerequisites

Node.js >= 18
npm

Project Structure

mcp-server-webscan/
├── src/
│   └── index.ts    # Main server implementation
├── dist/           # Compiled JavaScript
├── package.json
└── tsconfig.json

Building

npm run build

Development Mode

npm run dev

Error Handling

The server implements comprehensive error handling:

Invalid parameters
Network errors
Content parsing errors
URL validation

All errors are properly formatted according to the MCP specification.

Contributing

Fork the repository
Create your feature branch (git checkout -b feature/amazing-feature)
Commit your changes (git commit -m 'Add some amazing feature')
Push to the branch (git push origin feature/amazing-feature)
Open a Pull Request

License

MIT License - see the LICENSE file for details