fetch-html-to-md
MCP server that fetches remote or local HTML resources and converts them to Markdown, enabling AI clients to summarize or process web content.
README
<div align="center">
<h1>fetch-html-to-md</h1>
Convert remote or local HTML resources to Markdown via CLI or Node.js API.
English | įŽäŊ䏿
</div>
đ Introduction
fetch-html-to-md is a lightweight, high-performance Node.js solution designed to bridge the gap between web content and structured Markdown. Built with flexibility in mind, it operates seamlessly both as a developer-friendly SDK and as an intuitive command-line utility.
Quick Start
npx @kabeep/fetch-html-to-md@latest https://example.com
MCP Server
npx @kabeep/fetch-html-to-md@latest mcp
đĻ Installation
As Node.js API
npm install @kabeep/fetch-html-to-md
As CLI
npm install --global @kabeep/fetch-html-to-md
âī¸ Usage
ESModule
import fetchHtml2md, {
html2md,
type Html2MdOptions
} from '@kabeep/fetch-html-to-md';
// 1. Facade Function: Automatically converts local file path or remote URL
const markdown = await fetchHtml2md('https://example.com', {
// ...Html2MdOptions
});
// 2. Built-in html-to-md
const rawMarkdown = html2md('<h1>Hello World</h1>');
CommonJS
const fetchHtml2md = require('@kabeep/fetch-html-to-md');
const { html2md } = require('@kabeep/fetch-html-to-md');
async function main() {
// 1. Facade Function
const markdown = await fetchHtml2md('./index.html');
console.log(markdown);
// 2. Built-in html-to-md
const rawMarkdown = html2md('<h1>Hello World</h1>');
}
CLI
Convert a local file
fetch-html-to-md ./docs/index.html
Convert a remote URL
fetch-html-to-md https://example.com
Pass a raw HTML string to convert
fetch-html-to-md --raw "<strong><em>strong and italic</em></strong>"
Read from stdin
echo https://example.com | fetch-html-to-md
Use Options
fetch-html-to-md ./index.html --skip-tags div section --alias-tags "figure=p"
đŠ CLI Options
Input Options
Note: Input flags are mutually exclusive. Only one input source can be provided per execution.
| Option | Short | Type | Description |
|---|---|---|---|
[uri] |
- | string |
Positional argument. Path to a local HTML file or a remote URL. |
--url |
- | string |
Specify an HTML page URL. |
--filepath |
-f |
string |
Specify a local HTML file path. |
--raw |
- | boolean |
Pass a raw HTML string directly instead of [uri] for conversion. |
Configuration Options
See more: https://github.com/stonehank/html-to-md/blob/HEAD/README-EN.md#configoptional
| Option | Type | Default | Description |
|---|---|---|---|
--skip-tags |
array |
(native) | Tags to skip rendering while keeping their inner content intact. (space-separated list) |
--empty-tags |
array |
[] |
Tags to skip along with all content inside them. |
--ignore-tags |
array |
(native) | Tags to completely ignore (both tag and content). |
--alias-tags |
array |
- | Rename HTML tags using key=value pairs. <br>(e.g., --alias-tags figure=p dd=p) |
--render-custom-tags |
enum |
'true' |
Rule for non-standard HTML tags. <br>Choices: 'true', 'false', 'SKIP', 'EMPTY', 'IGNORE' |
--force |
boolean |
false |
Force custom configurations to overwrite native defaults. |
General Options
| Option | Short | Description |
|---|---|---|
--help |
-h |
Display help menu and command options. |
--version |
-v |
Display package version. |
đ MCP Server
The fetch-html-to-md CLI natively supports the Model Context Protocol (MCP).
This enables AI clients such as Claude Desktop, Cursor, and Windsurf
to seamlessly invoke it as a background tool for web scraping and local HTML
conversion.
1. Client Setup
Add the following snippet to your client configuration file (e.g.,
claude_desktop_config.json or .cursor/mcp.json):
{
"mcpServers": {
"fetch-html-to-md": {
"command": "npx",
"args": [
"-y",
"@kabeep/fetch-html-to-md",
"mcp"
]
}
}
}
2. Tool Schema
The MCP server exposes a default tool named fetch_html_to_md with the
following parameters:
| Parameter | Type | Required | Description |
|---|---|---|---|
uri |
string |
Yes | Target webpage URL (http:// or https://) or local HTML file path |
đŦ Example Prompt
Once configured, you can simply ask your AI assistant:
"Fetch https://example.com using fetch_html_to_md and summarize the key takeaways."
đ Credits
- html-to-md - A JS library for convert HTML<String> to markdown<String>, gzip 10kb.
đ¤ Contribution
Contributions via Pull Requests or Issues are welcome.
đ License
This project is licensed under the MIT License. See the LICENSE file for details.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.