Html To Markdown Mcp

io.github.MukundaKattaPublished by GitHub account MukundaKattav0.1.0Updated Oct 24, 2026

Convert HTML to Markdown or strip to plain text. For web-scraping agents.

VerifiedSTDIODesktop onlyWeb Search & ScrapingDeveloper Tools

Overview

AI-generated overview

A local MCP server that converts HTML into clean Markdown or plain text, giving assistants a deterministic way to turn scraped pages into readable content.

What you can do
Convert HTML to Markdown with consistent headings, fenced code and inline links, stripping scripts and styles by default. Strip HTML entirely and return whitespace-normalized plain text, a faster option when only text is needed.
When to use it
Useful for web-scraping or read-the-page agents that need stable Markdown or text output instead of letting the model convert HTML inline, which varies between turns. Not a full content-extraction pipeline, so main-content detection must happen separately.
Requirements
Runs locally over stdio, installed via npx from the npm package @mukundakatta/html-to-markdown-mcp. No authentication, environment variables or headers are declared. Desktop clients only.
Before you install
Conversion is local and read-only; no credentials, payments or writes are involved. Output quality depends on the input HTML, and it does not detect main content, so navigation and boilerplate may remain.

Installation

In SourceWeft

  1. Open Html To Markdown Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

@mukundakatta/html-to-markdown-mcp

MCP server for HTML → Markdown conversion. For web-scraping and read-the-page agents.

Tools

  • html_to_md(html, ...options) — Turndown-based conversion with sane defaults (ATX headings, fenced code, inline links). Strips scripts/styles by default.
  • extract_text(html) — strip everything, return whitespace-normalized text. Faster than html_to_md when you only need text content.

Why this exists

Web-scraping agents constantly need clean Markdown from HTML. LLMs do this inline but inconsistently across turns (different heading styles, different list markers, sometimes leaving raw HTML tags in). A deterministic converter avoids the variance.

This is intentionally not a full content-extraction pipeline (no Readability-style "main content" detection — use that in a separate step if needed).

Install — Claude Desktop

json
{  "mcpServers": {    "html-to-markdown": { "command": "npx", "args": ["-y", "@mukundakatta/html-to-markdown-mcp"] }  }}

Same shape for Cursor / Cline / Windsurf / Zed.

License

MIT OR Apache-2.0.

Source: packages/html-to-markdown-mcp/README.md at commit 6fad5bb

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts