html-to-markdown-mcp
by levz0r
Overview
Converts HTML content (from a URL or raw string) into clean, formatted Markdown and can save it to a file.
Installation
npx html-to-markdown-mcpSecurity Notes
The server has critical security vulnerabilities. The `saveToFile` and `filePath` parameters in the `html_to_markdown` and `save_markdown` tools are resolved using `path.resolve()`, allowing for **Path Traversal / Arbitrary File Write**. An attacker could specify paths like `../../../etc/passwd` to write to arbitrary locations on the server's file system. Additionally, the `url` parameter in `html_to_markdown` allows fetching from any URL, posing a **Server-Side Request Forgery (SSRF)** risk, enabling an attacker to make requests to internal networks or cloud metadata endpoints.
Similar Servers
scrapi-mcp
Serves as a Model Context Protocol (MCP) server that utilizes the ScrAPI service to scrape web pages and return their content in either HTML or Markdown format.
deep-research-mcp
Facilitates comprehensive web research using Tavily Search and Crawl APIs to gather, aggregate, and structure information for LLM-powered markdown documentation generation via the Model Context Protocol.
markitdown-mcp
A Model Context Protocol (MCP) server for converting over 29 file formats (PDFs, Office docs, images, audio, etc.) into clean, structured Markdown, primarily for integration with AI workflows and MCP clients like Claude Desktop.
mcp-server-requests
An MCP server that provides HTTP request capabilities, enabling LLMs to fetch and process web content, including saving to files.