Web Fetch
Retrieves real-time web content from specified URLs, providing text summaries and data extraction capabilities.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add web-fetch npx -- -y @trustedskills/web-fetch
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"web-fetch": {
"command": "npx",
"args": [
"-y",
"@trustedskills/web-fetch"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
The web-fetch skill enables AI agents to retrieve data from websites by fetching and parsing HTML content. It supports extracting specific elements, such as text or links, and can be used for tasks like scraping information or monitoring web pages.
When to use it
- Extracting product details from an e-commerce site for price comparison.
- Monitoring news articles on a blog for updates or changes in content.
- Gathering contact information from business directories for lead generation.
Key capabilities
- Fetches HTML content from URLs
- Parses and extracts specific elements from web pages
- Supports filtering based on CSS selectors or tags
Example prompts
- "Fetch the latest headlines from https://example-news-site.com."
- "Extract all product names and prices from the homepage of https://example-store.com."
- "Get the contact email from the 'About Us' section of https://example-business.com."
Tips & gotchas
- Ensure that website terms of service allow scraping or fetching data.
- Some sites may block automated requests, so consider using headers or delays to avoid being flagged.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.