This MCP server converts HTML webpages to clean Markdown format, significantly reducing HTML size while preserving essential content like tables and images.
From the registry: Converts HTML to Markdown with auto-summary and section extraction. Supports Playwright.
$ git clone https://github.com/sunshad0w/html2md-mcp.git && cd html2md && uv pip install -e .$ playwright install chromiumPlease install the `html2md` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Clone and install** — Clone the repository and install in editable mode with uv (or pip) Run: `git clone https://github.com/sunshad0w/html2md-mcp.git && cd html2md && uv pip install -e .`
- **Python 3.10+** — Python 3.10 or higher required
Optional prerequisites:
- Install Playwright browsers — Install Chromium for browser mode (required for JS-heavy sites) Run: `playwright install chromium`
Canonical MCP server config (stdio transport):
- command: `uv`
- args: ["--directory","/absolute/path/to/html2md","run","html2md"]
Note: Not published as npm/PyPI package — requires cloning. Docker image also available as an alternative ('docker run -i --rm html2md'). Playwright browser mode supports JS-heavy and authenticated pages.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.MCP server for Firecrawl web scraping, structured data extraction and web search integration.