npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

read-web-page-mcp

v3.0.0

Published

MCP server for reading web pages - works with OpenClaw

Readme

read-web-page MCP

MCP server that provides a read_web_page tool for AI agents. Uses a smart multi-layered fallback chain to read any URL reliably.

How It Works

ANY URL → fetch (instant)
           ├── Got real content? → return ✅
           └── Empty/broken?
                ├── Twitter/X? → FXTwitter (<1s) → Jina (~8s) → Playwright (last resort)
                └── Other URL? → Jina (~8s) → Playwright (last resort)

Each layer tries the lightest option first. Playwright (headless Chrome) only fires if everything else fails.

Features

  • ✅ Multi-layer fallback chain (fetch → FXTwitter → Jina → Playwright)
  • ✅ Twitter/X optimized via FXTwitter API (instant, clean JSON)
  • ✅ Handles JavaScript-heavy sites (Playwright as last resort)
  • ✅ Converts HTML to Markdown
  • ✅ Content extraction with cheerio (removes nav, sidebars, ads)
  • ✅ Junk content detection (error pages, login walls)
  • ✅ Simple caching (24h TTL)
  • ✅ Objective-based filtering (returns relevant excerpts)
  • ✅ Browser instance reuse (no cold start per request)
  • ✅ Optional Jina API key for higher rate limits

Setup

npm install
npm run build

Environment Variables (optional)

# Jina API key — bumps rate limit from 20 to 500 RPM
export JINA_API_KEY=your_key_here

Usage with AI Agents

Add to your agent config:

Local instance:

{
  "mcpServers": {
    "read-web-page": {
      "command": "node",
      "args": ["/path/to/dist/index.js"]
    }
  }
}

Via npx:

{
  "mcpServers": {
    "read-web-page": {
      "command": "npx",
      "args": ["read-web-page-mcp"]
    }
  }
}

VPS instance (remote):

{
  "mcpServers": {
    "read-web-page": {
      "command": "ssh",
      "args": ["[email protected]", "node /path/to/dist/index.js"]
    }
  }
}

Tool API

read_web_page

| Parameter | Type | Required | Description | |-----------|------|----------|-------------| | url | string | ✅ | The URL to read | | objective | string | ❌ | What info you're looking for (returns relevant excerpts) | | forceRefetch | boolean | ❌ | Skip cache, fetch live |

Returns: Markdown-formatted content

Providers

| Provider | Speed | Best For | Needs Setup | |----------|-------|----------|-------------| | fetch | instant | Static sites, blogs, docs | None | | FXTwitter | <1s | Tweets, X posts | None | | Jina | ~8s | JS-heavy sites, X articles | Optional API key | | Playwright | ~7s | Last resort, complex pages | Chromium installed |

Performance

| Scenario | Provider Used | Time | |----------|--------------|------| | Static website | fetch | <1s | | Tweet | FXTwitter | ~2s | | X long-form article | Jina | ~3s | | JS-heavy app (worst case) | Playwright | ~7s | | Cached request | cache | <1ms |

Architecture

Agent ── stdio ──→ MCP Server
                      │
                      ├── fetch (native HTTP)
                      ├── FXTwitter API (api.fxtwitter.com)
                      ├── Jina Reader API (r.jina.ai)
                      └── Playwright (headless Chromium)

Install from npm

npm i read-web-page-mcp