webustler
by titan77champion
Overview
Webustler is designed for extracting clean, markdown text from any URL, including Cloudflare-protected sites, primarily for local desktop use.
Installation
python server.pyEnvironment Variables
- TIMEOUT
Security Notes
The server's fallback mechanism (`_fetch_fallback`) posts user-provided URLs to `http://localhost:8191/v1` for scraping. If this MCP server is deployed publicly, this constitutes a severe Server-Side Request Forgery (SSRF) vulnerability, allowing attackers to make the server request arbitrary URLs on its local network or external targets. Even as a local desktop application, it poses a risk by allowing malicious URLs to potentially interact with other local services on the user's machine. The primary scraping method also forwards user URLs to an external service (`r.jina.ai`), which could be a risk if `jina.ai`'s service is vulnerable to URL manipulation.
Similar Servers
tomcp
Converts any website into an MCP (Model-Config-Protocol) server for AI tools and enables AI chat with website content by converting HTML to clean Markdown.
scrapegraph-mcp
Provides AI-powered web scraping, structured data extraction, multi-page crawling, and agentic automation capabilities for language models.
html-to-markdown-mcp
Converts HTML content from web pages or raw strings into Markdown format, with options for including metadata, truncating content, and saving to files.
scrapi-mcp
This MCP server enables AI agents to scrape web pages and retrieve their content as HTML or Markdown, with advanced browser interaction capabilities.