MCP HTML Extractor for Openclaw

A specialized Model Context Protocol (MCP) server designed for seamless web scraping and HTML data extraction via mcporter.

claudedamir-art
v1.0.0
May 11, 2026
0
657
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install jarvis-mcp-html

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install jarvis-mcp-html using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).

Prefer to download?

Get the raw skill files in a ZIP archive.

What is MCP HTML Extractor?

The MCP HTML Extractor is a robust tool designed to bridge the gap between static web content and AI agents. As part of the ecosystem of Openclaw Skills, it allows developers and automated agents to programmatically fetch URLs, parse HTML, and isolate valuable information such as raw text and hyperlinks.

Built to operate over the Model Context Protocol, this skill integrates with mcporter to provide a standardized interface for web data retrieval. It transforms unstructured websites into structured inputs that LLMs can process, making it an essential utility for research, data collection, and automated browsing tasks.

MCP HTML Extractor Use Cases

  • Extracting clean text content from articles or documentation for AI summarization.
  • Gathering all hyperlinks from a landing page to map site structures.
  • Automating web data collection workflows within Openclaw Skills environments.
  • Feeding real-time web data into LLM prompts for grounded context.

How MCP HTML Extractor Works

  1. The user or agent initiates a request through the mcporter CLI using the stdio transport layer.
  2. The MCP HTML Extractor receives the target URL and fetches the remote HTML content.
  3. The server processes the DOM to extract specific elements like text or anchors based on the chosen tool.
  4. Structured results are returned to the agent in a format suitable for immediate analysis or storage.

MCP HTML Extractor Setup

To get started with this member of the Openclaw Skills family, ensure you have Node.js installed and run the following commands:

npm install -g html-extractor-mcp

You will also need mcporter installed to call the tools via the command line.

MCP HTML Extractor Data Schema & Taxonomy

The skill utilizes a request-response schema via MCP tools. Below are the primary interaction points:

Tool Name Input Parameter Output Type
fetch url (string) Full HTML / JSON API Response
extract_text url (string) Cleaned Text String

Metadata is handled via the Openclaw specification, requiring the mcporter and html-extractor-mcp binaries to be present in the system path.

MCP HTML Extractor Advanced Features

  • Direct integration with mcporter for standardized tool calling.
  • Lightweight execution with minimal resource footprint via demand-based stdio launching.
  • Capability to handle JSON API calls alongside standard HTML extraction.
  • Seamless compatibility with other Openclaw Skills for complex agentic workflows.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*