MCP Webscan Server
by MCP-Mirror
The MCP Webscan Server is a Model Context Protocol (MCP) server designed for web content scanning and analysis. It provides tools for fetching, analyzing, and extracting information from web pages.
Last updated: N/A
What is MCP Webscan Server?
The MCP Webscan Server is a tool that allows users to fetch, analyze, and extract information from web pages using the Model Context Protocol (MCP). It provides functionalities like converting web pages to Markdown, extracting links, crawling websites, checking for broken links, finding URL patterns, and generating sitemaps.
How to use MCP Webscan Server?
To use the server, first clone the repository, install dependencies using npm install, and build the project with npm run build. Then, start the server using npm start. The server runs on stdio transport and can be integrated with MCP clients like Claude Desktop by configuring the server details in the client's settings. You can then use the available tools by calling them with the appropriate parameters.
Key features of MCP Webscan Server
Page Fetching (to Markdown)
Link Extraction
Site Crawling
Link Checking
Pattern Matching
Sitemap Generation
Use cases of MCP Webscan Server
Content analysis of web pages
Website auditing for broken links
Data extraction from websites
Generating sitemaps for SEO
Automated web content monitoring
FAQ from MCP Webscan Server
How do I fetch a web page?
How do I fetch a web page?
Use the fetch_page tool with the url parameter.
Can I crawl an entire website?
Can I crawl an entire website?
Yes, use the crawl_site tool with the starting url and optionally specify the maxDepth.
How do I check for broken links on a page?
How do I check for broken links on a page?
Use the check_links tool with the url parameter.
How do I find URLs matching a specific pattern?
How do I find URLs matching a specific pattern?
Use the find_patterns tool with the url and pattern parameters.
How do I generate a sitemap for a website?
How do I generate a sitemap for a website?
Use the generate_sitemap tool with the root url and optionally specify the maxUrls.