MCP Fetch

Retrieve and extract text or raw HTML from URLs with robots.txt compliance.

2|Updated Mar 10, 2026

Search Tags:#information retrieval #web scraping #content extraction #url fetch #web crawler

Ready to run

npx skills add https://github.com/caoronglin/copaw-skills --skill mcp-fetch

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: MCP Fetch
Source: https://github.com/caoronglin/copaw-skills/tree/main/skills/mcp-fetch
Command: npx skills add https://github.com/caoronglin/copaw-skills --skill mcp-fetch

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates the process of retrieving content from web pages, making it easy to access and process information from the internet without manual browsing.

Core Features & Use Cases

Web Page Scraping: Extracts text, titles, and links from any given URL.
Format Flexibility: Supports returning simplified content or raw HTML.
Robots.txt Compliance: Adheres to website crawling rules by default.
Use Case: Quickly gather the main text content of a news article from a URL to summarize it or extract key information.

Quick Start

Fetch the content from the URL https://example.com/article.

Frequently Asked Questions about MCP Fetch

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I extract main text content from a web page URL for information retrieval?▼

To extract content for information retrieval, provide the target web page URL to fetch the main text, titles, and links. The skill handles character encoding automatically and returns simplified text or raw HTML.

Does this web scraping tool respect robots.txt crawling rules by default?▼

Yes, this web scraping tool adheres to robots.txt rules by default. It ensures your content extraction and web crawler activities respect website crawling restrictions without requiring manual configuration.

Can I get raw HTML instead of simplified text when fetching URL content?▼

Yes, you can retrieve raw HTML instead of simplified text when fetching URL content. The format flexibility allows you to specify raw HTML output for tasks requiring original page structure and link extraction.

What is the best way to automate web page scraping for content aggregation?▼

The best way to automate web page scraping for content aggregation is to supply the target URLs to the skill. It automatically handles character encoding and extracts titles, links, and text without manual browsing.

Will character encoding issues affect web content extraction from international sources?▼

No, character encoding issues will not affect web content extraction. The skill handles character encoding automatically, ensuring accurate text retrieval and content aggregation from international online sources.

When should I not use this URL fetch approach for web scraping?▼

You should not use this URL fetch approach if a website strictly prohibits web scraping in its robots.txt file. The tool adheres to crawling rules by default, which may block extraction from restricted sources.